The DOI matches its Crossref record; 159 of the 166 references it cites were found in a registry or an index; 7 of the 137 sources its claims cite were checked for support.
Survey of Temporal Information Retrieval and Related Applications
Open accessAbstract
Temporal information retrieval has been a topic of great interest in recent years. Its purpose is to improve the effectiveness of information retrieval methods by exploiting temporal information in documents and queries. In this article, we present a survey of the existing literature on temporal information retrieval. In addition to giving an overview of the field, we categorize the relevant research, describe the main contributions, and compare different approaches. We organize existing research to provide a coherent view, discuss several open issues, and point out some possible future research directions in this area. Despite significant advances, the area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches. Moreover, an effective end-to-end temporal retrieval system that exploits temporal information to improve the quality of the presented results remains undeveloped.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This survey reviews temporal information retrieval (T-IR), organizing prior work on temporal annotation, extraction from web resources, and temporal web IR tasks such as crawling, indexing, query processing, ranking, clustering, classification, search engines, and future-related retrieval. It concludes that despite advances, the area lacks a systematic overview and an effective end-to-end temporal retrieval system remains undeveloped.
Key findings
- T-IR combines traditional document relevance with temporal relevance; timeliness/currency is treated as one of five key aspects of document quality, alongside relevance, accuracy, objectivity, and coverage.
- Explicit temporal queries are rare: about 1.5% of all queries [Nunes et al. 2008], reduced to 1.21% after accounting for false positives [Campos et al. 2011b]. Implicit temporal query studies report varying profiles: 54% atemporal and 46% temporally ambiguous [Jones and Diaz 2007]; only 7% implicit temporal [Metzler et al. 2009]; 10% never spiked, 47% spiked once, and 43% spiked multiple times [Kulkarni et al. 2011]; 75% atemporal and 25% implicit temporal [Campos et al. 2011c].
- Temporal tagger evaluations: GUTime achieved F1 0.85 for recognition and 0.82 for normalization on TERN 2004; in TempEval-2, SuTime achieved the best extraction F1 of 0.92 versus HeidelTime’s 0.86, while HeidelTime achieved the best normalization F1 of 0.85 versus SuTime’s 0.82.
- Web temporal evidence: among 62,842 web snippets, roughly 10% contain explicit temporal information; among 508 web snippets, 82.48% of future dates relate to the near future and 17.52% to a further future. The Internet Archive reportedly grows at 100 terabytes per month and has over 350 billion archived web pages, later cited as more than 357 billion.
Methods
- Design: literature survey of existing T-IR research; it categorizes relevant research, describes main contributions, compares approaches, organizes existing research, and discusses open issues and future directions.
- Data/sample: no primary dataset or experiment; it synthesizes prior literature and references datasets/collections such as TimeBank, TimeML, the New York Times Annotated Corpus, ClueWeb09/12, web query logs, web snippets, news archives, and Twitter.
- Analysis: qualitative narrative synthesis and taxonomy across temporal annotation, temporal information extraction, web temporal feature extraction (metadata, content, usage), and temporal web IR stages including crawling, indexing, query processing, ranking, clustering, classification, search engines, and future-related retrieval.
Limitations
- Stated in the paper: the area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches; an effective end-to-end temporal retrieval system that exploits temporal information to improve result quality remains undeveloped.
- Stated in the paper: evaluation is difficult because the community often lacks a gold standard; most research has a rather specific scope; query log access outside industry is impeded by privacy/legal concerns; temporal taggers are often language- and domain-specific; metadata timestamps are often unavailable or unreliable and may differ from focus time.
- Evident from the text: as a survey, it presents no new empirical experiments or primary validation; its findings and numbers are drawn from cited studies, so coverage and conclusions depend on the selected literature.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
7 of 137 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured
- Premisecitation
Berberich et al. 2005 introduced T-Rank Light and T-Rank, based on link analysis, taking into account freshness and activity of pages and links to retrieve recent documents.
“[Berberich et al. 2005] introduced two approaches based on link analysis, T-Rank Light and T-Rank, taking into account both the freshness (i.e., the timestamps of the most recent updates) and the activity (i.e., update rates) of pages as well as links to retrieve recent documents.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Berberich et al. 2005 source
- Premisecitation
Campos et al. 2012b, 2014 identified relevant temporal expressions extracted from web snippets by clustering documents sharing a common relevant year, using GTE.
“[Campos et al. 2012b, Campos et al. 2014] who identified the relevant temporal expressions extracted from web snippets by clustering in which documents were grouped into the same cluster if they share a common relevant year.”
Quote in the paperNot a substantial claim1 of 2 sources checked- cites Campos et al. 2012b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Campos et al. 2014 source
- Premisecitation
Inagaki et al. 2010 proposed temporal click features and query reformulation chains to improve machine learning recency-sensitive ranking.
“[Inagaki et al. 2010] also proposed a set of novel temporal click features and query reformulation chains to improve the machine learning recency-sensitive ranking”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Inagaki et al. 2010 source
The Introduction says the authors propose temporal click features to improve machine-learned recency ranking and leverage query chains to smooth those features. It describes query reformulation chains as an existing concept, rather than something the authors proposed. (LLM, conf=0.87)
Experimental — accuracy not yet measured
- Premisecitation
Styskin et al. 2011 relied on a recency-sensitive query classifier to apply result diversification by combining ordinary search results with fresh documents.
“[Styskin et al. 2011] who relied on a recencysensitive query classifier to apply result diversification by combining ordinary search results with fresh documents.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Styskin et al. 2011 source
- Findingnone given
Few tackled the problem of determining the document focus time, especially in the case of lack or scarcity of temporal expressions.
“While some methods determine a document's timestamp, few tackled the problem of determining the document focus time, especially in the case of the lack or the scarcity of temporal expressions within the document content.”
Quote in the paperSubstantial claim
- Findingcitation
A significant amount of near-term future-related information refers to events scheduled to happen until the end of the current calendar year.
“This work compares the amount and the typical topics of information related to the near or distant future and finds that significant amount of near-term future-related information refers to the events scheduled to happen until the end of current calendar year.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2010 source
- Findingreasoning
None of the research studies has proposed time period query expansion.
“However, none of the research studies has proposed time period query expansion”
Quote in the paperNot a substantial claim - Findingreasoning
Current IR systems still do not sufficiently exploit temporal information despite documents being full of temporal expressions and many having strong temporal characteristics.
“However, despite the fact that documents are full of temporal expressions and many have strong temporal characteristics, current IR systems still do not sufficiently exploit this information.”
Quote in the paperSubstantial claim- Rests on an assumption: Documents are full of temporal expressions and many have strong temporal characteristics.
- Interpretationcitation
Access to real-world query logs outside big industrial labs is particularly difficult and a huge impediment to information retrieval research.
“Although relying on web query logs may be a valid solution to infer the temporal value of implicit temporal queries, access to real-world query logs outside big industrial labs is particularly difficult and a huge impediment to information retrieval research.”
Quote in the paperNot a substantial claim - Interpretationnone given
YAGO2 fails to extract information from free text corpora, which is a limitation.
“However, like its predecessor it fails to extract information from free text corpora, which is a limitation.”
Quote in the paperNot a substantial claim - Premisecitation
Kuzey and Weikum 2012 is an extension of T-YAGO and YAGO2.
“Another recent approach is the work of [Kuzey and Weikum 2012], which is an extension of T-YAGO and YAGO2.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kuzey and Weikum 2012 source
- Interpretationcitation
Access to the document timestamp or even to contextual clues, although important, might not be enough in the case of more ambiguous phrases.
“Besides, access to the document timestamp or even to contextual clues, although important, might not be enough in the case of more ambiguous phrases.”
Quote in the paperNot a substantial claim - Interpretationreasoning
A temporal index solution does not solve the problem of false positive temporal query expressions whose time period fits within the document's time span.
“Although such a solution may be a step toward achieving a fully integrated temporal information retrieval solution, it still does not solve the problem of false positive temporal query expressions whose time period fits within the document's time span.”
Quote in the paperSubstantial claim - Premisecitation
Wang et al. 2011 proposed PRAVDA to automatically harvest temporal facts from textual web sources, especially from news articles and biography texts.
“[Wang et al. 2011] proposed PRAVDA to automatically harvest temporal facts from textual web sources, especially from news articles and biography texts.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al. 2011 source
- Premisecitation
The difficulty in accessing query logs is mostly due to legal concerns about privacy issues.
“As pointed out by [Callan and Moffat 2012], this is mostly due to legal concerns about privacy issues.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Callan and Moffat 2012 source
- Premisecitation
A few recent works have explored temporal information for the automatic development of temporal knowledge bases.
“A few recent works [Wang et al. 2010, Hoffart et al. 2011, Wang et al. 2011, Wang et al. 2012, Talukdar et al. 2012, and Kuzey and Weikum 2012] have explored such temporal information for the automatic development of temporal knowledge bases.”
Quote in the paperNot a substantial claim0 of 3 sources checked - Premisecitation
T-YAGO uses regular expressions to extract temporal facts from semi-structured data attached to Wikipedia articles, such as infoboxes.
“T-YAGO uses regular expressions to extract temporal facts from semi-structured data attached to Wikipedia articles, such as infoboxes.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al. 2010 source
- Premisecitation
Most detected temporal expressions in online news articles occur in a two-year long time window with regard to the document timestamp.
“This is shown in Fig. 8, where most of the detected temporal expressions occur in a two-year long time window with regard to the document timestamp and the near past and the near future tend to be referred to by fine granularity expressions, such as days.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt and Yeung 2011 source
- Interpretationreasoning
Detecting the freshness of a web page can be quite difficult since temporal metadata are neither necessarily provided nor trustworthy.
“However, detecting the freshness of a web page can be quite difficult since temporal metadata are neither necessarily provided nor trustworthy.”
Quote in the paperSubstantial claim - Premisecitation
Web servers typically do not provide other temporal information than the crawling date.
“One reason for this, as observed by [Nunes et al. 2007], is due to the fact that web servers typically do not provide other temporal information than the crawling date.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Nunes et al. 2007 source
- Premisecitation
The near past and the near future tend to be referred to by fine granularity expressions, such as days.
“This is shown in Fig. 8, where most of the detected temporal expressions occur in a two-year long time window with regard to the document timestamp and the near past and the near future tend to be referred to by fine granularity expressions, such as days.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt and Yeung 2011 source
- Interpretationreasoning
Kuzey and Weikum 2012 allows the construction of an enhanced knowledge base when compared to T-YAGO and YAGO2.
“This allows the construction of an enhanced knowledge base when compared to T-YAGO and YAGO2.”
Quote in the paperNot a substantial claim - Interpretationcitation
Metadata information is particularly difficult to obtain from less structured collections, such as web pages, as opposed to news articles.
“In addition, metadata information is particularly difficult to obtain from less structured collections, such as web pages, as opposed to news articles.”
Quote in the paperNot a substantial claim - Premisecitation
Issuing a query following a real-world change may still result in outdated information being retrieved due to the self-correcting latency of the web.
“For example, [Yamamoto et al. 2007] demonstrated that issuing a query following a real-world change (e.g., nomination of a new president or a change in such numerical values as a country's population or the number of EU states) may still result in outdated information being retrieved due to the self-correcting latency of the web.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yamamoto et al. 2007 source
- Premisecitation
Applying temporal approaches to non recency-sensitive queries might harm the quality of the search results.
“This may actually constitute a problem because, as reported by [Efron and Golovchinsky 2011], applying temporal approaches to non recency-sensitive queries might harm the quality of the search results.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Efron and Golovchinsky 2011 source
- Interpretationreasoning
It is generally quite difficult to determine trustworthy metadata based on information extracted during the crawling process.
“Indeed, as discussed in Section 3.1, it is generally quite difficult to determine (with a high degree of certainty) trustworthy metadata (i.e., document creation time, document publication time, or last-modified date) based on information extracted during the crawling process.”
Quote in the paperSubstantial claim - Interpretationnone given
Most pioneering approaches have tackled recency-sensitive query detection based on newswire collections using query volume and the number of published documents as an indicator of the query's recency sensitiveness.
“Most pioneering approaches have tackled this problem based on newswire collections using query volume and the number of published documents as an indicator of the query's recency sensitiveness.”
Quote in the paperNot a substantial claim - Interpretationreasoning
Retrieving relevant documents related to explicit temporal queries can be problematic when the query contains false positive temporal expressions.
“Even though retrieving relevant documents related to explicit temporal queries appears to be a straightforward process, it can be problematic when the query contains such false positive temporal expressions.”
Quote in the paperNot a substantial claim - Premisecitation
Wang et al. 2012 employs a methodology that combines label propagation and an integer linear program that incorporates temporal constraints among correlated events to determine noisy facts.
“As above, [Wang et al. 2012] employs a methodology that combines label propagation and an integer linear program that incorporates temporal constraints among correlated events to determine noisy facts (e.g., Cristiano Ronaldo cannot play football for Manchester United and Real Madrid at the same time).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al. 2012
- Interpretationreasoning
Implicit temporal expressions are often difficult to position in time due to the lack of a clear temporal purpose or an unambiguously associated time point.
“They are often difficult to position in time due to the lack of a clear temporal purpose or an unambiguously associated time point.”
Quote in the paperNot a substantial claim - Interpretationreasoning
A completely comprehensive search feature is often missing in most time search mechanisms.
“Although extensively diffused in text search systems, a completely comprehensive search feature is often missing in most time search mechanisms.”
Quote in the paperNot a substantial claim - Premisecitation
YAGO2 focuses on temporal and spatial knowledge by gathering information from Wikipedia infobox attributes, WordNet and GeoNames.
“Another extension of the YAGO knowledge base is the YAGO2 system [Hoffart et al. 2011], which focuses on temporal and spatial knowledge by gathering information from Wikipedia 23 infobox attributes, WordNet 24 and GeoNames.25”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Hoffart et al. 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
Jong et al. 2005 and Kanhabua and Nørvåg 2008 approached the problem by determining the time of non-timestamped documents using temporal language models.
“[Jong et al. 2005] and [Kanhabua and Nørvåg 2008] approached this problem by determining the time of nontimestamped documents, namely, news articles, resorting to temporal language models”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jong et al. 2005
- cites Kanhabua and Nørvåg 2008 source
- Premisecitation
Dong et al. 2010a proposed a retrieval system to answer recency-sensitive breaking news queries.
“[Dong et al. 2010a] proposed a retrieval system to answer recency-sensitive breaking news queries.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dong et al. 2010a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
Kanhabua and Nørvåg 2010 used a query's determined time to improve reranking of web page results.
“[Kanhabua and Nørvåg 2010] used a query's determined time to improve the reranking of the web page results.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kanhabua and Nørvåg 2010 source
- Premisecitation
Li and Croft 2003 introduced time-based language models as an extension of Ponte and Croft 1998 to favor documents created in recent time.
“they introduced the notion of time-based language models as an extension of work proposed by [Ponte and Croft 1998] to favor documents created in recent time.”
Quote in the paperNot a substantial claim0 of 2 sources checked - Interpretationreasoning
With current text mining techniques, it has become possible to measure society's attention and focus when remembering past events and topics.
“With current text mining techniques, it has now become possible to measure society's attention and focus when it comes to remembering past events and topics.”
Quote in the paperNot a substantial claim - Premisecitation
The first initiative pushed the most recent web pages to the top list of results by freshness metrics that take into account the document timestamp.
“The first initiative, as pointed out by [Manica et al. 2012], which is still used today, pushed the most recent web pages to the top list of the results by freshness metrics that take into account the document timestamp”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Manica et al. 2012 source
- Interpretationreasoning
The approach proposed by Metzler et al. lacks query coverage since it depends on the analysis of query logs.
“However, the approach lacks query coverage since it depends on the analysis of query logs.”
Quote in the paperNot a substantial claim - Premisecitation
Arikan et al. 2009 were the first to propose an approach that integrates temporal expressions extracted from document content in a language modeling framework.
“[Arikan et al. 2009] were the first to propose an approach that integrates temporal expressions extracted from the document content in a language modeling framework.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Arikan et al. 2009
- Premisecitation
Kanhabua and Nørvåg 2012 proposed a time-sensitive ranking model based on learning-to-rank techniques for explicit temporal queries.
“[Kanhabua and Nørvåg 2012] proposed a new approach by applying a time-senstive ranking model based on learning-to-rank techniques for explicit temporal queries.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kanhabua and Nørvåg 2012 source
- Premisecitation
Jatowt et al. 2009 proposed two methods to summarize future-related information in web pages and news articles.
“[Jatowt et al. 2009] proposed two methods to summarize future-related information in web pages and news articles.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2009 source
- Premisecitation
Elsas and Dumais 2010 developed a language model based ranking algorithm that incorporates dynamics of document content changes using term frequency distribution over time.
“[Elsas and Dumais 2010] developed a language model based ranking algorithm that incorporates the dynamics of document content changes using term frequency distribution over time.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Elsas and Dumais 2010 source
- Premisecitation
Cheng et al. 2013 presented a language ranking model that incorporates a timeliness factor to retrieve fresh recent results for non-spike timely queries.
“[Cheng et al. 2013] presented a language ranking model that incorporates the timeliness factor to retrieve fresh recent results for non-spike timely queries.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Cheng et al. 2013 source
- Premisecitation
Li et al. 2008 tried to improve PageRank by assigning a non-fixed damping factor governed by a function that depends on time elapsed since last update.
“[Li et al. 2008] tried to improve PageRank by assigning a non-fixed dumping factor governed by a function that depends on the time that elapsed since the last update of the pages.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Li et al. 2008
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
The results show that SVM MAP learning-to-rank model outperforms the proposed method of Berberich et al. 2010.
“The results show that SVM MAP learning-to-rank model outperforms the proposed method of [Berberich et al. 2010].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Berberich et al. 2010 source
- Premisecitation
Kawai et al. 2010 presented an approach to filter out noisy year expressions from web snippets that are temporally irrelevant to a query.
“[Kawai et al. 2010] presented an approach to filter out noisy year expressions 𝑦 from web snippets 𝑠 that are temporally irrelevant to query q”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kawai et al. 2010 source
- Interpretationreasoning
None of the above models extracted temporal information from web contents.
“While the above models rely on spikes in the distribution of relevant documents or queries, none extracted temporal information from web contents.”
Quote in the paperSubstantial claim - Premisecitation
The obtained results show that the introduction of GTE improves the quality of generated clusters by retrieving a higher number of relevant dates than previous approaches.
“The obtained results show that the introduction of GTE improves the quality of generated clusters by retrieving a higher number of relevant dates than previous approaches”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Campos et al. 2012b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Campos et al. 2014 source
Checked before — its earlier verdict is held back until a new check runs.
- Premisecitation
Vicente-Diez and Martinez 2009 proposed a temporal expression recognition and normalization system for Spanish contents integrated into a web search engine prototype.
“[Vicente-Diez and Martinez 2009] proposed a temporal expression recognition and normalization system for Spanish contents that has been integrated into a web search engine prototype.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Vicente-Diez and Martinez 2009 source
- Premisecitation
Strötgen et al. 2012 proposed the first approach to identify the most relevant temporal expressions in text documents.
“[Strötgen et al. 2012], who proposed the first approach to identify the most relevant temporal expressions in text documents.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Strötgen et al. 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
Li and Croft 2003 was one of the first works that implemented recency-sensitive ranking.
“One of the first works that implemented recency-sensitive ranking was proposed by [Li and Croft 2003].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Li and Croft 2003 source
- Premisecitation
Strötgen and Gertz 2013 presented a novel ranking approach that takes into account proximity of text, temporal, and geographic query terms.
“Finally [Strötgen and Gertz 2013] presented a novel ranking approach that takes into account the proximity of text, temporal, and geographic query terms in documents”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Strötgen and Gertz 2013 source
- Interpretationreasoning
Volume-based techniques cannot be applied to non-spiky queries because the number of published documents or issued queries does not clearly reflect their temporality.
“However, in this case, volume-based techniques cannot by applied, since the number of published documents or issued queries does not clearly reflect their temporality.”
Quote in the paperSubstantial claim - Premisecitation
Aji et al. 2010 introduced a new term weighting model that uses revision history analysis (RHA) of a document to redefine a term's importance.
“[ Aji et al. 2010] introduced a new term weighting model that uses the revision history analysis (RHA) of a document to redefine a term's importance”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Aji et al. 2010 source
- Premisecitation
Baeza-Yates 2005 was the first to suggest a future search engine and future-related information retrieval.
“[Baeza-Yates 2005] was the first to suggest a future search engine and future-related information retrieval.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Baeza-Yates 2005
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisenone given
Determining a document's timestamp was first studied by Toyoda and Kitsuregawa 2006 and Nunes et al. 2007.
“Determining a document's timestamp was first studied by [Toyoda and Kitsuregawa 2006] and [Nunes et al. 2007].”
Quote in the paperNot a substantial claim0 of 2 sources checked - Premisecitation
Jatowt et al. 2013a takes a statistical approach based on data derived from large news collections to estimate document focus time.
“More recent work on document focus time estimation [Jatowt et al. 2013a] takes a statistical approach based on data derived from large news collections.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2013a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
In its traditional form, the PageRank algorithm fails to promote newly created relevant web pages because acquiring links usually requires considerable time.
“In its traditional form, the PageRank algorithm fails to promote newly created relevant web pages because acquiring links usually requires considerable time.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Baeza-Yates et al. 2002 source
- Interpretationreasoning
Traditional search engines will likely retrieve more recent web pages about the competition that will occur in 2014 instead of information about the 1950 tournament.
“Traditional search engines however, will likely retrieve more recent web pages about the competition that will occur in 2014 instead of information about the 1950 tournament.”
Quote in the paperNot a substantial claim - Premisecitation
The fact that all these studies are built on top of temporal language models involves drawbacks concerning document collection.
“Finally, as observed by [Kanhabua and Nørvåg 2010], the fact that all these studies are built on top of temporal language models involves drawbacks concerning document collection.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kanhabua and Nørvåg 2010 source
- Interpretationreasoning
This method is of little relevance to users interested in more historical information.
“However, this method is of little relevance to users interested in more historical information.”
Quote in the paperNot a substantial claim - Interpretationreasoning
A user searching for information about 'Blaise Pascal' will hardly obtain relevant data about the date of his death or about his well-known works when applying such a filter.
“For example, a user searching for information about”
Quote in the paperNot a substantial claim - Premisecitation
Jatowt and Yeung 2011 extended the above concepts by taking into account the uncertainty of a piece of future-related information.
“[Jatowt and Yeung 2011] extended the above concepts by taking into account the uncertainty of a piece of future-related information.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt and Yeung 2011 source
- Premisecitation
Chang et al. 2012 re-ranked search results based on user intents at different times of day using user temporal click information from query logs.
“[Chang et al. 2012] re-ranked the search results based on user intents at different times of day using the user temporal click information obtained from query logs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Chang et al. 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisereasoning
Cho et al. 2005 relied on web link structure evolution to propose a new ranking metric to solve the problem pointed out by Baeza-Yates et al. 2002.
“[Cho et al. 2005] relied on web link structure, especially its evolution, to propose a new ranking metric to solve the problem pointed out by [Baeza-Yates et al. 2002]”
Quote in the paperNot a substantial claim0 of 2 sources checked - Premisecitation
Berberich et al. 2007b implemented FluxCapacitor, a time-travel text search prototype.
“[Berberich et al. 2007b] implemented FluxCapacitor a time-travel text search prototype”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Berberich et al. 2007b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Interpretationnone given
Only one study [Campos et al. 2012a] has taken up the research of extracting temporal information from web contents.
“To the best of our knowledge only one study [Campos et al. 2012a] has taken up this research so far.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Campos et al. 2012a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
Perkiö et al. 2005 automatically detected topical trends and their importance over time within a news corpus using a simple variant of TF.IDF.
“[Perkiö et al. 2005] automatically detected topical trends and their importance over time within a news corpus using a simple variant of TF.IDF.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Perkiö et al. 2005 source
- Premisecitation
Jatowt et al. 2011 first addressed the problem of determining focus time.
“Such an approach was first addressed by [Jatowt et al. 2011].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Premisecitation
Baeza-Yates et al. 2002 demonstrated the temporal bias of PageRank.
“who demonstrated the temporal bias of PageRank.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Baeza-Yates et al. 2002 source
- Premisecitation
The task of supporting searches for future-related information is critical since a significant number of users are looking for content about future events.
“The task of supporting searches for future-related information is critical since a significant number of users are looking for content about future events [Joho et al. 2013].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Joho et al. 2013 source
- Interpretationreasoning
IR systems poorly obtain the historical or up-to-date perspectives of some subjects because they may prevent returning relevant documents more or less uniformly distributed over time.
“On the other hand, since it may prevent returning relevant documents more or less uniformly distributed over time, IR systems poorly obtain the historical or up-to-date perspectives of some subjects.”
Quote in the paperSubstantial claim - Interpretationreasoning
When a user's information quest includes temporal aspects, traditional IR systems may fail because they continue to treat temporal expressions as normal text terms.
“As an example, when a user's information quest includes temporal aspects, traditional IR systems may fail because they continue to treat temporal expressions as normal text terms.”
Quote in the paperSubstantial claim- Rests on an assumption: Traditional IR systems continue to treat temporal expressions as normal text terms.
- Interpretationreasoning
Neglecting the temporal dimension is a key search signal that some content has been omitted.
“What these two examples show is that neglecting the temporal dimension is a key search signal that some content has been omitted.”
Quote in the paperSubstantial claim
- Probably not a substantial claim. 151
- It may state two separate claims as one. 32
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationGUTime extends the capabilities of TempEx by adding TIMEX3 tags.
“Another temporal tagger is GUTime which extends the capabilities of TempEx [Mani and Wilson 2000] by adding TIMEX3 tags.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Mani and Wilson 2000 source
The Overall Architecture section describes a temporal tagger that identifies and resolves time expressions, supporting the reference to an earlier tagger. But the copy does not name it TempEx or say that GUTime extends it by adding TIMEX3 tags (searched: GUTime, TempEx, TIMEX3). (LLM, conf=0.85)
Experimental — accuracy not yet measured
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationRelative temporal expressions depend on the document publication date or another date near in the context.
“Relative temporal expressions, which were referenced for the first time in 1998 during MUC-7 [Setzer and Gaizauskas 2000], depend on the document publication date or another date near in the context.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Setzer and Gaizauskas 2000 source
The Introduction reports that MUC-7 (1998) extended the named-entity task to relative time expressions, and §3.1.2 says such expressions can be relative to the document date. Section 3.1.2 also discusses using context to interpret a date, but our copy does not specifically say that the reference is another nearby date. Page numbers are unavailable in our copy. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationZhang et al. 2009 described a re-ranking score adjustment to give a ranking boost to fresh documents.
“Next [Zhang et al. 2009] described a re-ranking score adjustment to give a ranking boost to fresh documents.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites Zhang et al. 2009 source
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Findingnone givenTo the best of our knowledge, there are only a limited number of prototypes in this field.
“To the best of our knowledge, there are only a limited number of prototypes in this field.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Findingnone givenWith the growth of research in temporal information retrieval, search engines have started to exploit time to improve their search processes.
“With the growth of research in temporal information retrieval, search engines have started to exploit time to improve their search processes.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Findingnone givenIt is necessary to wade through more than 60 web pages in the Google engine search results to find the first reference to the 1950 event.
“Indeed, it is necessary to wade through more than 60 web pages in the Google engine search results to find the first reference to the 1950 event.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Findingnone givenWorks on temporal ranking can be broadly divided into two classes: recency-sensitive ranking and time-sensitive ranking.
“several works have been proposed that can be broadly divided into two classes: (1) those favoring more recent documents (recency-sensitive ranking) and (2) those that target documents from different time periods (time-sensitive ranking).”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
FindingreasoningResearchers have started to address the problem of returning documents that are not only topically relevant but also from the most important time periods.
“researchers have started to address the problem of returning documents that are not only topically relevant but that are also from the most important time periods.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
Findingnone givenSeveral research works have been proposed, leading to the emergence of a number of search engine temporal applications.
“To tackle this problem several research works have been proposed, leading to the emergence of a number of search engine temporal applications.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
FindingreasoningBoth classes of temporal ranking are closely related to the categories defined in the query processing section.
“Both classes are closely related to the categories defined in the query processing section”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Findingnone givenTo the best of our knowledge, only three studies have been proposed on temporal clustering of web page results.
“To the best of our knowledge, only three studies have been proposed.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper may give no reason why it holds.
Findingnone givenMost popular search engines do not explicitly consider the use of temporal information extracted from web pages.
“However, most popular search engines do not explicitly consider the use of the temporal information extracted from web pages”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
FindingreasoningThe construction of an effective end-to-end temporal system remains proposed.
“and the construction of an effective end-to-end temporal system remain proposed.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Findingnone givenThe temporal visualization of documents is still underexploited by internet users.
“This issue remains unanswered as the temporal visualization of documents is still underexploited by internet users.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
FindingcitationFor trending queries, displaying new temporal content can be quite useful for users.
“Their results suggest that for trending queries, displaying new temporal content can be quite useful for users.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Svore et al. 2012 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
FindingcitationWikipedia tends to lag about two hours behind Twitter in terms of page tweets and page views related to the same real-world events.
“They also discovered that Wikipedia tends to lag about two hours behind Twitter in terms of page tweets and page views related to the same realworld events.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Osborne et al. 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
Findingnone givenStep (2) of temporal image retrieval has been well studied so far, and many successful methods have been proposed.
“Step (2) has been well studied so far, and many successful methods have been proposed.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper may give no reason why it holds.
Findingnone givenSystems continue to adopt a simplistic approach that reduces temporal expressions to a single point in time rather than to a time span.
“systems continue to adopt a simplistic approach that reduces temporal expressions to a single point in time rather than to a time span.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationExplicit temporal queries represent about 1.5% of all queries.
“Such queries represent about 1.5% of all queries [Nunes et al. 2008].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Nunes et al. 2008
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenThese knowledge bases provide countless factual relations among entities, such as people or locations.
“These knowledge bases provide countless factual relations among entities, such as people or locations.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
Interpretationnone givenIt is not easy to retrieve web documents so that their temporal dimension will meet the user temporal intent underlying the query.
“Third, it is not easy to retrieve web documents so that their temporal dimension will meet the user temporal intent underlying the query.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationThe greatest difficulty in developing an automatic system for detecting temporal expressions is the large diversity of ways in which time can be expressed.
“The greatest difficulty in developing an automatic system for detecting temporal expressions is the large diversity of ways in which time can be expressed [Mazur 2012].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mazur 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim.
InterpretationreasoningOne consequence of ignoring the temporal dimension is the inconsistency of information, since some facts might only have been true for a particular time.
“One consequence is the inconsistency of information, since some facts might only have been true for a particular time (e.g., the relation [Bill Clinton, president of the USA] is only valid from 1993 to 2001).”
Quote in the paperSubstantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationcitationThe creation of annotation standard corpora like TimeBank, annotation schemas such as TimeML, and the development of temporal taggers indicate T-IR's importance.
“In addition, note the creation of annotation standard corpora like the TimeBank [Pustejovsky et al. 2006], annotation schemas such as TimeML 10 [Pustejovsky et al. 2003], and the development of temporal taggers [Strötgen and Gertz 2010a].”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Pustejovsky et al. 2006
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Pustejovsky et al. 2003
- cites Strötgen and Gertz 2010a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationLabel propagation, a semi-supervised learning algorithm, computes the confidence scores of the candidate facts.
“Then label propagation, a semi-supervised learning algorithm, computes the confidence scores of the candidate facts.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al. 2011 source
Probably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenLeveraging temporal information enables researchers to create knowledgeable retrieval mechanisms that support entity-level temporal queries instead of keyword-based ones.
“Leveraging such temporal information enables researchers to create knowledgeable retrieval mechanisms that support entity-level temporal queries instead of keyword-based ones.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenThe lack of an extensive collection of texts annotated with temporal information covering different languages forms an additional problem.
“Moreover, the lack of an extensive collection of texts annotated with temporal information covering different languages forms an additional problem.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation75% of implicit temporal queries based on web snippets are atemporal.
“In contrast to the above studies, [Campos et al. 2011c] addressed the profile of implicit temporal queries based on a collection of web snippets and found that 75% are atemporal and 25% have an implicit temporal nature.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Campos et al. 2011c
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningExtracting metadata from document content demands a rule definition for each different case or language, which may be quite unfeasible for real-world applications.
“This procedure demands a rule definition for each different case or language, which may be quite unfeasible for real-world applications.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationOnly 7% of queries have an implicit temporal nature.
“[Metzler et al. 2009] in turn, relied on web query logs to infer the implicit temporal values of queries based on similar explicit temporal queries, concluding that only 7% have an implicit temporal nature.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Metzler et al. 2009 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAnnie was developed in 2002 as part of the GATE distribution.
“Annie was also developed in 2002 as part of the GATE 18 distribution [Cunningham et al. 2002].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Cunningham et al. 2002
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
It may state two separate claims as one.
InterpretationreasoningT-YAGO's restriction to the football domain and its inability to support extraction of information from free text corpora limits its scope.
“Although an interesting first approach, its restriction to the football domain and the fact that it does not support the extraction of information from free text corpora limits its scope.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation43% of queries spiked multiple times (temporal ambiguous queries).
“A more recent study [Kulkarni et al. 2011] explored query intent changes over 10-week time spans and found that 10% of the queries never spiked (atemporal queries), 47% spiked once (temporal unambiguous queries), and 43% spiked multiple times (temporal ambiguous queries).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kulkarni et al. 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationResearch on extracting relational facts from text corpora has led to the emergence of large knowledge bases, such as DBpedia, YAGO, Freebase, and Wolfram Alpha.
“There has also been research on extracting relational facts (e.g., Barack Obama is the president of the USA) from text corpora, which has led to the emergence of large knowledge bases, such as DBpedia 19 [Auer et al. 2007], YAGO 20 [Suchanek et al. 2007] as well as commercial ones, such as Freebase 21 [Bollacker et al. 2007] and Wolfram Alpha 22 .”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
InterpretationreasoningAll of these large-scale projects clearly suggest T-IR's high interest to the public and that it constitutes a promising new research area.
“All of these large-scale projects clearly suggest T-IR's high interest to the public and that it constitutes a promising new research area.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
Interpretationnone givenWhile temporal taggers play an important role in temporal information processing, some works simply use straightforward regular expressions to look for temporal instances.
“While temporal taggers play an important role in temporal information processing, some works simply use straightforward regular expressions to look for temporal instances.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationShaparenko et al. correlated topic events with texts used in a document collection to provide an overview of how topics evolve over time.
“[Shaparenko et al. 2005] correlated topic events with texts used in a document collection to provide an overview of how topics evolve over time.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shaparenko et al. 2005
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenMost user information needs are implicit by nature.
“Even though some user information needs may be explicitly expressed, most are implicit by nature.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenResearchers also approached the problem of determining various temporal dimensions of documents and queries.
“They also approached the problem of determining various temporal dimensions of documents and queries.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation46% of TREC ad hoc queries belong to the temporally ambiguous class.
“[Jones and Diaz 2007] asked a few annotators to classify 51 TREC ad hoc queries using TREC topic descriptions and concluded that 54% of the queries belong to the atemporal class and 46% belong to the temporally ambiguous one.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jones and Diaz 2007 source
Probably not a substantial claim.
Interpretationnone givenA clear understanding of the temporal nature of queries is difficult due to query ambiguity, different temporal characteristics of queries or unknown users' expectations towards the temporality of search results.
“Second, a clear understanding of the temporal nature of queries is difficult due to query ambiguity, different temporal characteristics of queries or even unknown users' expectations towards the temporality of search results.”
Quote in the paperSubstantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
Interpretationnone givenThese contributions can greatly benefit the process of indexing documents, as well as the ranking of web search results or the clustering of documents.
“These contributions can greatly benefit the process of indexing documents, as well as the ranking of web search results or the clustering of documents.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
PremisecitationKuzey and Weikum 2012 harvests temporal facts and events from Wikipedia, especially from infoboxes of articles devoted to named events, and also extracts temporal facts from free text, namely from the full content of Wikipedia articles.
“As well as harvesting temporal facts and events from Wikipedia, especially from the infoboxes of articles devoted to named events (e.g., historical events, conferences, etc), it also extracts temporal facts from free text, namely, from the full content of Wikipedia articles.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kuzey and Weikum 2012 source
Probably not a substantial claim.
InterpretationreasoningFinding the document timestamp or related explicit temporal expressions is important so that a relative temporal expression can be mapped directly on the timeline as an explicit expression.
“As such, finding the document timestamp or related explicit temporal expressions is important, so that the expression can be mapped directly on the timeline as an explicit expression.”
Quote in the paperSubstantial claimIt may state two separate claims as one.
Premisenone givenHeidelTime achieved the best performance for the normalization process with an F1-measure of 0.85 as opposed to SuTime which achieved a score of 0.82.
“In contrast, HeidelTime achieved the best performance for the normalization process with an F 1 -measure of 0.85 as opposed SuTime which achieved a score of 0.82.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
Interpretationnone givenThe overall T-IE process is usually conducted by temporal taggers, which follow rule-based approaches based on regular expressions or local grammar-based techniques and usually involve hard work by experts.
“The overall T-IE process is usually conducted by temporal taggers, which follow rulebased approaches that are based on regular expressions or local grammar-based techniques and usually involve hard work by experts.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
InterpretationreasoningSince a web page can refer to different points in time, its focus time is better represented by a set of time intervals delimited by the document's oldest and newest temporal references rather than as a single point in time.
“Naturally, since a web page can refer to different points in time, its focus time is better represented by a set of time intervals delimited by the document's oldest and newest temporal references rather than as a single point in time.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
Interpretationnone givenSince the web is heterogeneous, multi-lingual, multi-cultural, and highly multi-domain, ambiguity is common.
“Since the web is heterogeneous, multi-lingual, multi-cultural, and highly multi-domain, ambiguity is common.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationCoTS temporally scopes relational facts based on change detection in a time series of the number of facts from the Google Books Ngram and Gigaword datasets.
“In contrast, CoTS [Talukdar et al. 2012] temporally scopes relational facts based on change detection in a time series of the number of facts from the Google Books Ngram [Michel et al. 2011] and Gigaword [Graff et al. 2003] datasets.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Talukdar et al. 2012 source
- cites Michel et al. 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Graff et al. 2003
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationThe goal of the TDT project is the exploration of techniques that identify the occurrence of new events to follow their track over time.
“The goal of the TDT project, which was one of the first important research initiatives related to news management, is the exploration of techniques that identify the occurrence of new events to follow their track over time.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Allan et al. 1998
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
It may state two separate claims as one.
InterpretationcitationOverall, the results show that the web is constantly changing mainly due to the creation of more and more new pages and, to a lesser extent, the modification of the content of existing ones.
“Overall, the results show that the web is constantly changing mainly due to the creation of more and more new pages and, to a lesser extent, the modification of the content of existing ones.”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Premisenone givenSince 2004, after the introduction of the TERN task as part of the ACE program, Temporal Information Extraction has become an independent task.
“However, since 2004, after the introduction of the TERN task as part of the ACE program, Temporal Information Extraction (T-IE) has become an independent task.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationMakkonen and Ahonen-Myka suggested an alternative solution by comparing one document with another through a temporal similarity measure.
“[Makkonen and Ahonen-Myka 2003] suggested an alternative solution by comparing one document with another through a temporal similarity measure.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Makkonen and Ahonen-Myka 2003 source
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
Premisenone givenSuTime is optimized for English texts and HeidelTime is a multi-lingual temporal tagger (English, German, and Dutch) that is adapted not only to the news domain but also to narrative documents.
“SuTime is optimized for English texts and HeidelTime is a multi-lingual temporal tagger (English, German, and Dutch) that is adapted not only to the news domain but also to narrative documents.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenThe T-IE process consists of three main tasks: Extraction or Recognition of temporal expressions, Normalization, and Temporal Annotation.
“It consists of three main tasks.The first is the Extraction or Recognition of temporal expressions.The second is Normalization to unify the different ways in which temporal expressions can be expressed.Finally, the last task called Temporal Annotation expresses temporal expressions in a standard format.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
InterpretationreasoningOne reason for missing comprehensive search is that the process is treated as an inherent part of document processing, when in fact it should be an independent task supported by a two-layered index framework.
“One reason is that this process is treated as an inherent part of document processing, when in fact it should be an independent task, supported by a two-layered index framework, where both document and temporal features are considered.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
InterpretationreasoningWith the advent of the web, a huge amount of temporal data has become available.
“With the advent of the web, the world's largest collection of data, a huge amount of temporal data has become available.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenThe huge volume of the web makes temporal information retrieval a difficult task.
“The huge volume of the web, however, makes T-IR a difficult task.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenFor certain applications there may be no need to use temporal taggers since they may require very specific information, such as year mentions in texts.
“Indeed, for certain applications there may be no need to use temporal taggers since they may require very specific information, such as year mentions in texts.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
InterpretationreasoningNone of the publicly provided search query collections includes a wide range of explicit temporal queries, so the process of inferring the temporal nature of implicitly formulated queries is hampered.
“Since none of these collections includes a wide range of explicit temporal queries, the process of inferring the temporal nature of queries implicitly formulated is hampered.”
Quote in the paperSubstantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationTime is inherently associated with events.
“Time is inherently associated with events [Setzer and Gaizauskas 2000].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Setzer and Gaizauskas 2000 source
Checked before — its earlier verdict is held back until a new check runs.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenTempEx is a rule-based model that extracts temporal information, particularly explicit and relative temporal expressions, and labels them with TIMEX2 tags.
“It is a rule-based model that extracts temporal information, particularly explicit (e.g., December 24, 2009) and relative temporal expressions (e.g., Monday), and labels them with TIMEX2 tags.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenIdentification of temporal information is a non-trivial task that requires the preprocessing stage of a document that usually involves four steps.
“The identification of temporal information is a non-trivial task that requires the preprocessing stage of a document that usually involves four steps.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
Premiseown dataBoth SuTime and HeidelTime have been evaluated in the TempEval-2 challenge and achieved competitive results.
“Both have been evaluated in the TempEval-2 challenge and achieved competitive results.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
Interpretationnone givenThese knowledge bases often ignore the temporal dimension and mostly focus on identifying the most salient facts.
“However, they often ignore the temporal dimension (e.g., Barack Obama has been the president of the USA since 2008) and mostly focus on identifying the most salient facts.”
Quote in the paperSubstantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationSwan and Allan proposed a classical hypothesis test to discover time-dependent features that identify the important topics in text documents.
“[Swan andAllan 1999, Swan andJensen 2000] proposed a classical hypothesis test to discover time-dependent features that identify the important topics in text documents.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Swan andAllan 1999
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Swan andJensen 2000
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
It may state two separate claims as one.
Interpretationnone givenEven though document timestamp information is usually available in news documents, it is particularly difficult to locate within web documents.
“Even though such information is usually available in news documents, it is particularly difficult to locate within web documents, as we discuss in Section 3.1.1.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationNearly half of the 110 respondents stated that the information for which they search is related to the present.
“In their survey, nearly half of the 110 respondents stated that the information for which they search is related to the present (information on the same day); yet a significant fraction also searches for future-related or past-related information.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Joho et al. 2013 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationWhen addressing the time issue within database research areas, two types of time are usually distinguished: valid and transaction.
“When addressing the time issue within the realm of database research areas, two types of time are usually distinguished: valid and transaction [Snodgrass and Ahn 1985].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Snodgrass and Ahn 1985 source
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenThis temporal information can be found within a number of different web sources, from web query logs to collections of web pages or social networks such as Twitter.
“This information can be found within a number of different web sources, from web query logs to collections of web pages or social networks such as Twitter.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation47% of queries spiked once (temporal unambiguous queries).
“A more recent study [Kulkarni et al. 2011] explored query intent changes over 10-week time spans and found that 10% of the queries never spiked (atemporal queries), 47% spiked once (temporal unambiguous queries), and 43% spiked multiple times (temporal ambiguous queries).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kulkarni et al. 2011 source
It may state two separate claims as one.
InterpretationreasoningExtracting temporal information from web query logs implies that some versions of the query have already been issued, thus contributing to query-dependency.
“A further challenge is that, contrary to the extraction of information within metadata or web contents, which simply requires a set of web search results, extracting temporal information from web query logs implies that some versions of the query have already been issued, thus contributing to query-dependency.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningThe content approach implies an increased level of difficulty compared to metadata approaches because it usually involves linguistic analysis of texts.
“Unlike metadata approaches, the content approach implies an increased level of difficulty since it usually involves linguistic analysis of texts, as discussed in Section 2.5.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation25% of implicit temporal queries based on web snippets have an implicit temporal nature.
“In contrast to the above studies, [Campos et al. 2011c] addressed the profile of implicit temporal queries based on a collection of web snippets and found that 75% are atemporal and 25% have an implicit temporal nature.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Campos et al. 2011c
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation10% of queries never spiked (atemporal queries).
“A more recent study [Kulkarni et al. 2011] explored query intent changes over 10-week time spans and found that 10% of the queries never spiked (atemporal queries), 47% spiked once (temporal unambiguous queries), and 43% spiked multiple times (temporal ambiguous queries).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kulkarni et al. 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationThe multitude of different forms in which human language allows temporal information to be conveyed as well as language intricacy and ambiguity complicate the task of tagging temporal information in texts more than simply finding the part-of-speech functions of words.
“Additionally, the multitude of different forms in which human language allows temporal information to be conveyed [Mazur 2012] as well as language intricacy and ambiguity complicate the task of tagging temporal information in texts more than simply finding the part-of-speech functions of words.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mazur 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationPRAVDA uses a pattern-based approach to extract the temporal candidates of facts.
“It uses a patternbased approach to extract the temporal candidates of facts.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al. 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationA significant fraction of the 110 respondents also searches for future-related or past-related information.
“In their survey, nearly half of the 110 respondents stated that the information for which they search is related to the present (information on the same day); yet a significant fraction also searches for future-related or past-related information.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Joho et al. 2013 source
It may state two separate claims as one.
Premisenone givenFor the extraction process, SuTime achieved the best performance with a score of 0.92 in terms of F1-measure, while HeidelTime obtained 0.86.
“For the extraction process, SuTime achieved the best performance with a score of 0.92 in terms of F 1 -measure, while HeidelTime obtained 0.86.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
PremisecitationWang et al. 2010 developed the T-YAGO knowledge base, which is an extension of YAGO.
“One of the first works addressing this problem was developed by [Wang et al. 2010] with the T-YAGO knowledge base, which is an extension of YAGO [Suchanek et al. 2007].”
Quote in the paperNot a substantial claim0 of 2 sources checkedProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenAn increasing number of contests and workshops focus on the temporal aspects of information.
“Another indication of T-IR's importance is the realization of an increasing number of contests and workshops that focus on the temporal aspects of information.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenThe WayBack Machine still does not allow a free text query search.
“Unfortunately, the system still does not allow a free text query search.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningMost available temporal taggers are useful for only one language (typically English) and for one domain (usually the news domain).
“Hence, most available temporal taggers are useful for only one language (typically English) and for one domain (usually, the news domain).”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenResearchers started to address the problem of retrieving web pages that are not only topically relevant but also created during (or that refer to) the most relevant time periods.
“Nevertheless, researchers started to address the problem of retrieving web pages that are not only topically relevant but also created during (or that refer to) the most relevant time periods.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
PremisecitationOther challenges involve determining the document creation time, delimiting, classifying, and normalizing temporal expressions, recognizing events or determining their temporal order.
“Other challenges involve determining the document creation time, delimiting, classifying, and normalizing temporal expressions, recognizing events or determining their temporal order [Costa 2013].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Costa 2013
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenSuTime and HeidelTime have been developed based on a rule-based system to extract and normalize temporal expressions.
“More recently, SuTime and HeidelTime have been developed based on a rule-based system to extract and normalize temporal expressions.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationKumaran and Allan detected new stories by measuring the degree overlap of one story with those that occurred in the past.
“[Kumaran and Allan 2004], on the other hand, detected new stories by measuring the degree overlap of one story with those that occurred in the past.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kumaran and Allan 2004 source
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Premisenone givenTempEx was the first temporal expression tagger to be developed.
“TempEx was the first temporal expression tagger to be developed.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
InterpretationreasoningSince the web is constantly changing, it is becoming more difficult for search engines to maintain up-to-date indexes, which threatens the effectiveness of the search process and the usefulness of search results.
“Since the web is constantly changing, it is also becoming more difficult for search engines to maintain up-to-date indexes, which threatens the effectiveness of the search process and the usefulness of search results.”
Quote in the paperSubstantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
PremisecitationAn integer linear program incorporating temporal constraints temporally scopes the correlated facts and guarantees their temporal consistency.
“As done above, an integer linear program incorporating temporal constraints temporally scopes the correlated facts and guarantees their temporal consistency.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Talukdar et al. 2012 source
Probably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenSince the web is constantly changing, maintaining up-to-date indexes is becoming more and more difficult.
“First, since the web is constantly changing, maintaining up-to-date indexes is becoming more and more difficult.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
Premisenone givenGUTime has been evaluated on the TERN 2004 training corpus and achieved F1-measure scores of 0.85 and 0.82 for temporal expression recognition and normalization, respectively.
“GUTime has been evaluated on the TERN 2004 training corpus and achieved F 1 -measure scores of 0.85 and 0.82 for temporal expression recognition and normalization, respectively.”
Quote in the paperNot a substantial claimProbably not a substantial claim.
InterpretationreasoningDetecting whether a query requires special treatment in terms of recency analysis is difficult, given that user search intents are usually underspecified.
“Detecting whether a query requires special treatment in terms of recency analysis is difficult, given that user search intents are usually underspecified.”
Quote in the paperSubstantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationImplicit temporal expressions require that at least a year appears somewhere close in the text to establish accurate temporal values.
“Therefore, as observed by [Alonso et al. 2009b], these expressions require that at least a year appears somewhere close in the text to establish accurate temporal values.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso et al. 2009b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisecitation54% of TREC ad hoc queries belong to the atemporal class.
“[Jones and Diaz 2007] asked a few annotators to classify 51 TREC ad hoc queries using TREC topic descriptions and concluded that 54% of the queries belong to the atemporal class and 46% belong to the temporally ambiguous one.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jones and Diaz 2007 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationInformation science researchers tend to consider timeliness or currency as one of the five key aspects that determine a document's quality; the others are relevance, accuracy, objectivity, and coverage.
“Information science researchers [Metzger 2007] tend to consider timeliness or currency as one of the five key aspects that determine a document's quality; the others are relevance, accuracy, objectivity, and coverage.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Metzger 2007
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenDespite the importance of time for information retrieval, research on time-sensitive fact extraction has only recently been addressed.
“Despite the importance of time for information retrieval, research on time-sensitive fact extraction has only recently been addressed.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
Interpretationnone givenThe process of searching for information is inherently temporal.
“The process of searching for information is inherently temporal.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Premisenone givenCommercial search engines have adopted this solution.
“Over the years, commercial search engines have adopted this solution.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenSuch information (creation date) is not available in many documents.
“Moreover, such information is not available in many documents.”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
Interpretationnone givenAll metadata-based approaches for identifying relevant query time periods rely on the creation date of documents as correct temporal signals, which are far from credible in most cases.
“Unfortunately, all of these approaches rely on the creation date of documents as correct temporal signals, which are far from credible in most cases.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationHolzmann et al. 2012 developed fokas, a search engine that offers user query suggestion terms based on named entity evolution.
“[Holzmann et al. 2012] developed fokas, which is a search engine that offers user query suggestion terms of the original query based on a named entity evolution procedure.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Holzmann et al. 2012
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenOther problems are related to the gap that exists between the document timestamp and the time to which the document contents refer.
“Other problems, as discussed in Section 3.1, are related to the gap that exists between the document timestamp and the time to which the document contents refer”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAlonso et al. 2007a presented an exploratory search interface that uses timelines to explain and explore search results.
“[Alonso et al. 2007a] presented an exploratory search interface that uses timelines to explain and explore search results.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso et al. 2007a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationThe process of determining a document's time dimension can be divided into two categories: determining a document's timestamp and determining its focus time.
“this process can be divided into two categories: (1) determining a document's timestamp, i.e., the time when the document was created, published or lastmodified and (2) determining its focus time, i.e., the time to which its contents refer.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kanhabua and Nørvåg 2008 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationYAGO2 provided a search interface to seek temporal and spatial knowledge facts in knowledge bases.
“YAGO2 [Hoffart et al. 2011] provided a search interface to seek temporal and spatial knowledge facts in knowledge bases.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Hoffart et al. 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationDong et al. 2010b incorporated fresh URLs extracted from Twitter into a general web search system.
“[Dong et al. 2010b] incorporated fresh URLs extracted from Twitter into a general web search system.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dong et al. 2010b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationKanhabua et al. 2011 proposed a ranking model for future predictions using a learning-to-rank algorithm.
“[Kanhabua et al. 2011] also proposed a ranking model for future predictions using a learning-to-rank algorithm”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kanhabua et al. 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationGarcia Fernandez et al. 2011 proposed a system to automatically determine the publication date of French historical documents based on unsupervised and supervised algorithms.
“[Garcia Fernandez et al. 2011] proposed a system to automatically determine the publication date of French historical documents based on unsupervised and supervised algorithms.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Garcia Fernandez et al. 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenGoogle has a time feature that allowed users to filter their search results.
“For example, Google has a time feature that allowed users to filter their search results.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationCampos et al. 2012b presented GTE-Cluster, an online temporal search interface.
“[Campos et al. 2012b] presented GTE-Cluster, an online temporal search interface”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Campos et al. 2012b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
InterpretationreasoningWhen an event is very likely to happen, usually the date and the time mentioned in news articles are more exact (finer granularity).
“When an event is very likely to happen, usually the date and the time mentioned in news articles are more exact (finer granularity).”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAlonso et al. 2009a introduced TCluster, an overlapping clustering algorithm.
“[Alonso et al. 2009a] introduced TCluster, an overlapping clustering algorithm”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso et al. 2009a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAlonso et al. 2009a proposed a measure to rank documents within a cluster based on the number of times a query occurs in a sentence with temporal expressions.
“[Alonso et al. 2009a] proposed a measure to rank documents within a cluster based on the number of times a query occurs in a sentence with explicit, implicit, and relative temporal expressions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso et al. 2009a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAlonso and Gertz 2006 described a prototype that provides users with an alternative presentation of results by a hit list of documents clustered by temporal attributes.
“[Alonso and Gertz 2006] described a prototype that provides users with an alternative presentation of the results by a hit list of documents clustered by temporal attributes.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso and Gertz 2006 source
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
Interpretationnone givenFuture-related information is inherently uncertain in contrast to past-related information.
“Particularly, future-related information is inherently uncertain in contrast to past-related information.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationShaparenko et al. 2005 tracked events over time by clustering.
“[Shaparenko et al. 2005] tracked events over time by clustering.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shaparenko et al. 2005
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenMost applications over digitalized archives fail to exploit the inherent temporal issue of historical collections.
“However, most fail to exploit the inherent temporal issue of historical collections.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
InterpretationreasoningThis solution may be very effective to filter in more detail recently published documents, but it may prove inefficient when the user is seeking timely information about a given topic.
“Although this solution may be very effective to filter in more detail recently published documents, it may prove inefficient when the user is seeking timely information about a given topic.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenFuture information retrieval is a promising T-IR trend that offers many advantages.
“Indeed, future information retrieval is a promising T-IR trend that offers many advantages”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenThe uncertainty of a future event influences the precision of temporal expressions in news articles.
“The uncertainty of a future event influences the precision of temporal expressions in news articles.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationStrötgen and Gertz 2010b presented TimeTrails for extraction, querying, storage, and exploration of spatio-temporal information.
“[Strötgen and Gertz 2010b], for example, presented a prototype system called TimeTrails for the extraction, querying, storage, and exploration of the spatio-temporal information stored in text documents.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Strötgen and Gertz 2010b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
PremisecitationSuch an approach is limited by two main constraints: the need to have a huge set of external documents and the requirement that last-modified dates exist in a set of external sources.
“Such an approach is limited however by two main constraints: (1) the need to have a huge set of external documents and (2) the requirement that the last-modified dates exist in a set of external sources”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Nunes et al. 2007 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationJin et al. 2008 proposed a new ranking algorithm applying linear interpolation of text similarity, temporal information, and page importance.
“[Jin et al. 2008] proposed a new ranking algorithm to sort results by applying a linear interpolation of three factors: text similarity, temporal information, and page importance.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jin et al. 2008 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationMatthews et al. 2010 proposed Time Explorer, a timeline search tool.
“[Matthews et al. 2010] proposed Time Explorer, a timeline search tool”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Matthews et al. 2010
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationAlonso et al. 2009a outlined a prototype implementation as a web interface where users can explore results by clusters.
“Another work [Alonso et al. 2009a] outlined a prototype implementation as a web interface where users can explore results by clusters returned in response to a query.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Alonso et al. 2009a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
PremisecitationDai and Davison 2010 estimated web page authority by determining variation of page and in-link freshness over time and incorporated this into T-Fresh.
“[Dai and Davison 2010] estimated the web page authority by determining the variation of page and in-link freshness over time and incorporated this information into a temporal ranking probabilistic model called T-Fresh.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dai and Davison 2010 source
Probably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenEstimating the relevance of a document can greatly benefit from the introduction of temporal aspects into ranking models.
“Estimating the relevance of a document can greatly benefit from the introduction of temporal aspects into ranking models.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationPredicting the popularity of queries by time series analysis and periodicity estimation is more reliable than straightforwardly using information on past query popularity derived from web query logs.
“Their results show that predicting the popularity of queries by time series analysis and periodicity estimation is more reliable than straightforwardly using information on past query popularity derived from web query logs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shokouhi and Radinsky 2012 source
It may state two separate claims as one.
PremisecitationAlonso et al. 2009a and Campos et al. 2012b introduced the notion of temporal clusters, which can be used to associate each document with a given time span.
“the works of [Alonso et al. 2009a] and [Campos et al. 2012b] introduced the notion of temporal clusters, which can also be used to associate each document with a given time span.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Alonso et al. 2009a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites Campos et al. 2012b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationJatowt et al. 2007 proposed using web archives to compare current and past versions of a web page to estimate approximate age of content elements.
“[Jatowt et al. 2007] proposed using web archives to compare the content of the current version of a web page with its past versions in order to estimate approximate age of different content elements on the page.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2007 source
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
Interpretationnone givenThe fact that the user has to specify a given time period naturally represents a shortcoming in terms of user experience.
“Moreover, the fact that the user has to specify a given time period naturally represents a shortcoming in terms of the user experience.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningThe validity of future-related information is a problem arising from the gap between the timestamp (e.g., creation time) and its reading time.
“One problem is the validity of future-related information, which arises from the gap between the timestamp (e.g., creation time) and its reading time.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationPasca 2008 proposed a temporal question answering system which defines regular expressions to detect dates that meet certain requirements.
“[Pasca 2008] proposed a temporal question answering system which defines regular expressions to detect dates that meet certain requirements.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Pasca 2008 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningThe probability of one event may be dependent on the probabilities of other related events.
“In other words, the probability of one event may be dependent on the probabilities of other related events.”
Quote in the paperNot a substantial claim- Rests on an assumption: Events are not totally independent from one another.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationKawai et al. 2010 proposed ChronoSeeker, an on-demand search engine.
“[Kawai et al. 2010] proposed an on-demand search engine called ChronoSeeker”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kawai et al. 2010 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationEfron 2012 proposed survival analysis to incorporate recency information into document ranking.
“[Efron 2012] proposed survival analysis 40 to incorporate recency information into document ranking”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Efron 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenThis approach is usually used by traditional search engines such as Google, Yahoo, and Bing in news domains or with spike phenomena.
“This approach is usually used by traditional search engines such as Google, Yahoo, and Bing in news domains or with spike phenomena”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
PremisecitationToyoda and Kitsuregawa 2006 and Nunes et al. 2007 used neighboring pages to estimate the document creation date or last-modified date.
“Both used neighboring pages to estimate the document creation date or the last-modified date”
Quote in the paperNot a substantial claim0 of 2 sources checkedProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenUsers will greatly benefit if a search engine system can explore the temporal information within web pages.
“Obviously, users will greatly benefit if a search engine system can explore the temporal information within web pages.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationJatowt and Yeung 2011 proposed a clustering algorithm to detect future events based on information extracted from a reference text corpus.
“[Jatowt and Yeung 2011] proposed a clustering algorithm to detect future events based on the information extracted from a reference text corpus.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt and Yeung 2011 source
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
InterpretationcitationThe used documents must be timestamped and cover the time period of the queries.
“In particular, the used documents must be timestamped and cover the time period of the queries.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationNunes et al. 2007 employed link structure analysis by considering three types of features: incoming links, outgoing links, and HTML src attributes.
“[Nunes et al. 2007] employed link structure analysis by considering three types of features derived from the web, incoming links, outgoing links, and HTML src attributes”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Nunes et al. 2007 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenA clear understanding of the query temporal nature offers search engines the chance to decide whether to return more historical or more recent information to provide the most relevant results.
“A clear understanding of the query temporal nature offers search engines the chance to decide whether to return more historical or more recent information to provide the most relevant results.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
InterpretationreasoningThis is particularly evident for implicit temporal queries.
“This is particularly evident for implicit temporal queries”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenA more elaborate mechanism gives users the possibility to specify a point-in-time or a temporal interval of their interest to filter out results outside that time period.
“A more elaborate mechanism gives users the possibility to specify a point-in-time or a temporal interval of their interest to filter out results outside that time period.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationJin et al. 2008 introduced TISE, a temporal search engine that supports content time retrieval for Chinese web pages.
“[Jin et al. 2008] introduced TISE, a temporal search engine that supports content time retrieval for Chinese web pages.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jin et al. 2008 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
PremisecitationJatowt et al. 2009 introduced a clustering approach to summarize future-related information using text content, content dates, and timestamps of future predictions.
“[Jatowt et al. 2009] introduced a clustering approach to summarize futurerelated information using text content, the content dates, and the timestamps of future predictions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jatowt et al. 2009 source
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenYahoo has been experimenting with basic temporal refinement in their web search engine to filter results by publication time.
“Yahoo, on the other hand, has been experimenting with basic temporal refinement in their web search engine to filter results by the publication time of the document”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence.
InterpretationreasoningText similarity cannot rely on words but rather on concepts.
“showing that text similarity cannot rely on words but rather on concepts.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenA further problem is the difficulty of evaluating research proposals, since the community still lacks a gold standard to which most approaches can be compared.
“A further problem is related to the difficulty of evaluating research proposals, since in many cases the community still lacks a gold standard to which most of the approaches can be compared.”
Quote in the paperNot a substantial claim- Rests on an assumption: The community still lacks a gold standard to which most approaches can be compared.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenThe availability of trustworthy temporal data allows posts to be arranged from the latest to the oldest.
“An important aspect of this is the availability of trustworthy temporal data that allows posts to be arranged from the latest to the oldest.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenPopular social networks like Facebook or Twitter include temporal evidence in their timelines and message posts.
“Popular social networks like Facebook or Twitter also include temporal evidence in their timelines and message posts.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenThere is much research on using temporal information for exploration and search purposes.
“There is also much research on using temporal information for exploration and search purposes.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Premisenone givenA temporal query can be used to obtain images of past or future objects.
“A temporal query can be used to obtain images of past or future objects (e.g., car).”
Quote in the paperNot a substantial claimIt may state two separate claims as one.
PremisereasoningBoth TempSum and KBA are constrained to the information on a given past event or entity and focus on a particular type of information, such as event attributes or event relations.
“Both TempSum and KBA are constrained to the information on a given past event or entity and focus on a particular type of information, such as event attributes or event relations.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningBoth subtasks of the TREC Temporal Summarization task have clear temporal characteristics because the discovered updates have to be timely and relevant.
“Both subtasks have clear temporal characteristics because the discovered updates have to be timely and relevant.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Premisenone givenA relatively large research focus has been put on using temporal information for exploration and search purposes.
“A relatively large research focus has been put on using temporal information for exploration and search purposes, as previously stated in Section 1.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenRecent development of research projects addresses the archiving, the analysis, and the access to the temporal web.
“Further evidence is the recent development of research projects that address the archiving, the analysis, and the access to the temporal web.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
InterpretationreasoningThe extraction of time references from Twitter messages can be a particularly difficult task mostly due to its informal communication style and short message length.
“The extraction of time references from twitter messages, however, can be a particularly difficult task mostly due to its informal communication style nature and short message length (e.g.,”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
Interpretationnone givenSimilar to the Temporal Summarization Task, the recency of information is critical.
“Similar to the Temporal Summarization Task, the recency of information is critical.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper may give no reason why it holds.
Interpretationnone givenIn recent years, time has been gaining increased importance in information retrieval and in a large number of its sub-areas.
“In recent years, time has been gaining increased importance in information retrieval and in a large number of its sub-areas.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Interpretationnone givenMicroblog collections pose new problems, mostly due to their short message length.
“This new type of data poses, however, some new problems, mostly due to its short message length.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
InterpretationreasoningThe highly dynamic characteristic of tweets can be better assessed to promote tweets with high informational value at given time points.
“In this way, the highly dynamic characteristic of tweets can be better assessed to promote tweets with high informational value at given time points.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence.
InterpretationreasoningA number of significant advances must be made before search engines can entirely understand the temporality of a query and correctly reflect it in their returned results.
“Thus, a number of significant advances must be made before search engines can entirely understand the temporality of a query and correctly reflect it in their returned results.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
Premisenone givenIn the area of temporal IR and temporal information extraction, several research challenges have been proposed.
“Likewise, in the area of temporal IR and temporal information extraction, several research challenges have been proposed.”
Quote in the paperNot a substantial claimProbably not a substantial claim. The paper’s conclusions may not depend on it.
PremisereasoningResearch in information retrieval and extraction is often fostered through the availability of standardized, open test collections and the proposals of task challenges.
“Research in information retrieval and extraction is often fostered through the availability of standardized, open test collections and the proposals of task challenges, thanks to which research communities can compare diverse approaches to the same problems.”
Quote in the paperNot a substantial claimProbably not a substantial claim. It may be too vague to check against evidence.
InterpretationreasoningThis recent research trend is still without immediate or at least visible effects for average users since most of the researches developed so far have a rather specific scope.
“Despite the growing importance of the area, this recent research trend is still without immediate or at least visible effects for average users since most of the researches developed so far have a rather specific scope.”
Quote in the paperNot a substantial claim- Rests on an assumption: Most researches developed so far have a rather specific scope.
The paper relies on this without support.
The area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches.
“Despite significant advances, the area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches.”
The paper relies on this without support.
An effective end-to-end temporal retrieval system that exploits temporal information to improve the quality of presented results remains undeveloped.
“Moreover, an effective end-to-end temporal retrieval system that exploits temporal information to improve the quality of the presented results remain undeveloped.”
The paper relies on this without support.
The value of information and its quality are intrinsically time-dependent.
“The value of information and its quality are intrinsically time-dependent.”
The authors state this as an assumption.
In web search scenarios, a document's reading time is the same as the time a search query was issued.
“In web search scenarios, a document's reading time is assumed to be the same as the time a search query was issued since users often access search results immediately after performing a search.”
The paper relies on this without support.
Events are not totally independent from one another.
“Often events are not totally independent from one another.”
The paper relies on this without support.
Newer information is more reliable than old information.
“In addition, paying attention to the timestamp of predictions is critical because newer information is more reliable than old information.”
The paper relies on this without support.
Microblog collections like tweets or Facebook posts usually include temporal information.
“Also important is the emergence of microblog collections, like tweets or Facebook posts that usually include temporal information.”
The paper relies on this without support.
Documents are full of temporal expressions and many have strong temporal characteristics.
“However, despite the fact that documents are full of temporal expressions and many have strong temporal characteristics, current IR systems still do not sufficiently exploit this information.”
The paper relies on this without support.
Traditional IR systems continue to treat temporal expressions as normal text terms.
“As an example, when a user's information quest includes temporal aspects, traditional IR systems may fail because they continue to treat temporal expressions as normal text terms.”
The paper relies on this without support.
Most researches developed so far have a rather specific scope.
“Despite the growing importance of the area, this recent research trend is still without immediate or at least visible effects for average users since most of the researches developed so far have a rather specific scope.”
The paper relies on this without support.
The community still lacks a gold standard to which most approaches can be compared.
“A further problem is related to the difficulty of evaluating research proposals, since in many cases the community still lacks a gold standard to which most of the approaches can be compared.”
The paper relies on this without support.
Image retrieval queries may sometimes have an explicit or implicit temporal intent.
“Like in document retrieval, image retrieval queries may sometimes have an explicit or implicit temporal intent.”
The paper relies on this without support.
In unstructured collections such as the web, many images do not contain explicit metadata that can be easily retrieved.
“However, in unstructured collections such as the web, many images do not contain explicit metadata that can be easily retrieved.”
The paper relies on this without support.
Predicting a query's temporal intent is a critical step to decide appropriate ranking.
“Predicting a query's temporal intent is a critical step to decide appropriate ranking.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Section 4.2 names different preprocessing steps from Section 2.5
MinorSection 4.2 says Section 2.5 already described tokenization, stopping, stemming, and information extraction. Section 2.5 instead lists tokenization, sentence extraction, part-of-speech tagging, and named-entity recognition as its four preprocessing steps.
“The component responsible for this task is the document processing module that requires the execution of four steps: tokenization, stopping, stemming, and information extraction, which were already described in Section 2.5.”
“The first one is Tokenization, which divides the text into words or phrases.The second is the Sentence Extraction process that identifies the set of all sentences in texts.The third is the part-ofspeech tagging (POS) process where tokens are assigned a part-of-speech.Finally, the fourth step, Named-entity Recognition (NER), identifies the proper nouns in documents.”
YAGO2 citation year differs from its reference
MinorThe text cites the Hoffart et al. YAGO2 work as 2011, but the matching YAGO2 entry in the references is dated 2013.
“Another extension of the YAGO knowledge base is the YAGO2 system [Hoffart et al. 2011]”
“66. Hoffart, J., Suchanek, F.M., Berberich, K., and Weikum, G. 2013. YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia.”
Reinanda citation year differs from its reference
MinorThe text cites Reinanda et al. as 2013, while the listed reference for Reinanda et al. is dated 2012.
“[Odijk et al. 2012, Reinanda et al. 2013, Michel et al. 2011, Matthews et al. 2010]”
“125. Reinanda, R., Odijk, D., and de Rijke, M. 2012. Exploring Entity Associations Over Time.”
Citations
Cites
The anatomy of a large-scale hypertextual Web search engine
Brin, S., & Page, L. (1998) · Computer Networks and ISDN Systems · doi:10.1016/s0169-7552(98)00110-x · Cited by 16,004
Maintaining knowledge about temporal intervals
Allen, J. F. (1983) · Communications of the ACM · doi:10.1145/182.358434 · Cited by 7,593 · cited 1×
“Another formal approach is the work of [Allen 1983], which introduces the notion of time intervals rather than fixed time points and describes a set of thirteen possible temporal relationships between two time intervals.”
BackgroundHalbwachs, M., & Coser, L. A. (1992) · doi:10.7208/chicago/9780226774497.001.0001 · Cited by 4,939
Earthquake shakes Twitter users
Sakaki, T., Okazaki, M., & Matsuo, Y. (2010) · International World Wide Web Conference (WWW) · doi:10.1145/1772690.1772777 · Cited by 3,631
Quantitative Analysis of Culture Using Millions of Digitized Books
Michel, J.-B., Shen, Y. K., Aiden, A. P., Veres, A., Gray, M. K., The Google Books Team, Pickett, J. P., Hoiberg, D., Clancy, D., Norvig, P., et al. (2010) · Science · doi:10.1126/science.1199644 · Cited by 3,235
Yago: a core of semantic knowledge
Suchanek, F. M., Kasneci, G., & Weikum, G. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242667 · Cited by 2,512
A Language Modeling Approach to Information Retrieval
Ponte, J. M., & Croft, W. B. (2017) · ACM SIGIR Forum · doi:10.1145/3130348.3130368 · Cited by 2,503
DBpedia: A Nucleus for a Web of Open Data
Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., & Ives, Z. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-76298-0_52 · Cited by 2,454
A language modeling approach to information retrieval
Ponte, J. M., & Croft, W. B. (1998) · Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/290941.291008 · Cited by 1,821
The role of social networks in information diffusion
Bakshy, E., Rosenn, I., Marlow, C., & Adamic, L. (2012) · Proceedings of the 21st international conference on World Wide Web · doi:10.1145/2187836.2187907 · Cited by 1,526
YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia
Hoffart, J., Suchanek, F. M., Berberich, K., & Weikum, G. (2012) · Artificial Intelligence · doi:10.1016/j.artint.2012.06.001 · Cited by 1,261
Inverted files for text search engines
Zobel, J., & Moffat, A. (2006) · ACM Computing Surveys · doi:10.1145/1132956.1132959 · Cited by 1,084
Topic Detection and Tracking Pilot Study Final Report
Allan, J., Carbonell, J., Doddington, G. R., Yamron, J., & Yang, Y. (2018) · doi:10.1184/r1/6626252.v1 · Cited by 942
The Anatomy of the Facebook Social Graph
Ugander, J., Karrer, B., Backstrom, L., & Marlow, C. (2011) · arXiv · doi:10.48550/arxiv.1111.4503 · Cited by 819
LifeLines: visualizing personal histories
Catherine Plaisant, B., Milash, B. A., Rose, A., Widoff, S., & Shneiderman, B. (1996) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/238386.238493 · Cited by 597
New York Times Annotated Corpus
Sandhaus, E., & Linguistic Data Consortium (2012) · TIB Data Manager · doi:10.57702/qbrk4fuh · Cited by 594
Ntoulas, A., Cho, J. J., & Olston, C. (2004) · International World Wide Web Conference (WWW) · doi:10.1145/988672.988674 · Cited by 452
Radinsky, K., Agichtein, E., Gabrilovich, E., & Markovitch, S. (2011) · International World Wide Web Conference (WWW) · doi:10.1145/1963405.1963455 · Cited by 405
SUTime: A library for recognizing and normalizing time expressions
Chang, A. X., & Manning, C. (2012) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/5pi53hxdrsdt · Cited by 383
SemEval-2013 Task 1: TempEval-3: Evaluating Time Expressions, Events, and Temporal Relations
UzZaman, N., Llorens, H., Derczynski, L., Allen, J. F., Verhagen, M., & Pustejovsky, J. D. (2013) · Cited by 336
HeidelTime: High Quality Rule-Based Extraction and Normalization of Temporal Expressions
Strötgen, J., & Gertz, M. (2010) · Cited by 293
Identifying similarities, periodicities and bursts for online search queries
Vlachos, M., Meek, C., Vagena, Z., & Gunopulos, D. (2004) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/1007568.1007586 · Cited by 276
Multilingual and cross-domain temporal tagging
Strötgen, J., & Gertz, M. (2012) · Language Resources and Evaluation · doi:10.1007/s10579-012-9179-y · Cited by 224
Text classification and named entities for new event detection
Kumaran, G., & Allan, J. (2004) · Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1008992.1009044 · Cited by 220
Dong, A., Zhang, R., Kolari, P., Bai, J., Díaz, F., Chang, Y., Zheng, Z., & Hongyuan Zha, B. (2010) · International World Wide Web Conference (WWW) · doi:10.1145/1772690.1772725 · Cited by 215
Kahle, B. (1997) · Scientific American · doi:10.1038/scientificamerican0397-82 · Cited by 213
Estimating frequency of change
Cho, J., & Garcia-Molina, H. (2003) · ACM Transactions on Internet Technology · doi:10.1145/857166.857170 · Cited by 196
A large-scale study of the evolution of web pages
Fetterly, D., Manasse, M., Najork, M., & Wiener, J. (2003) · Proceedings of the twelfth international conference on World Wide Web - WWW '03 · doi:10.1145/775152.775246 · Cited by 189
Mining the web to predict future events
Radinsky, K., & Horvitz, E. (2013) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2433396.2433431 · Cited by 188
SparkClouds: Visualizing Trends in Tag Clouds
Lee, B., Riche, N. H., Karlson, A. K., & Carpendale, S. (2010) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2010.194 · Cited by 182
On the value of temporal information in information retrieval
Alonso, O., Gertz, M., & Baeza-Yates, R. A. (2007) · ACM SIGIR Forum · doi:10.1145/1328964.1328968 · Cited by 174
Memento: Time Travel for the WebPreprint
Herbert Van De Sompel, A., Nelson, M. L., Sanderson, R., Balakireva, L., Ainsworth, S. G., & Shankar, H. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0911.1112 · Cited by 169
Towards recency ranking in web search
Dong, A., Chang, Y., Zheng, Z., Mishne, G., Bai, J., Zhang, R., Buchner, K., Liao, C. Y., & Díaz, F. (2010) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/1718487.1718490 · Cited by 167
Li, X., & Croft, W. B. (2003) · Proceedings of the twelfth international conference on Information and knowledge management · doi:10.1145/956863.956951 · Cited by 161
Adar, E., Teevan, J. B., Dumais, S., & Elsas, J. L. (2009) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/1498759.1498837 · Cited by 160
Jones, R., & Diaz, F. (2007) · ACM Transactions on Information Systems · doi:10.1145/1247715.1247720 · Cited by 147
The visual display of temporal information
Cousins, S. B., & Kahn, M. G. (1991) · Artif. Intell. Medicine · doi:10.1016/0933-3657(91)90005-v · Cited by 145
Robust temporal processing of news
Mani, I., & Wilson, G. (2000) · Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00 · doi:10.3115/1075218.1075228 · Cited by 142
A model for temporal references and its application in a question answering program
Bruce, B. C. (1972) · Artificial Intelligence · doi:10.1016/0004-3702(72)90040-9 · Cited by 134
Integration of news content into web results
Díaz, F. (2009) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/1498759.1498825 · Cited by 134
Clustering and exploring search results using timeline constructions
Alonso, O., Gertz, M., & Baeza-Yates, R. A. (2009) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1645953.1645968 · Cited by 133
Temporal Information Retrieval: Challenges and Opportunities
Alonso, O., Strötgen, J., Baeza-Yates, R. A., & Gertz, M. (2011) · Cited by 125
TimeMines : Constructing Timelines with Statistical Models of Word Usage
Swan, R. C. (2000) · Cited by 111
A Survey on Web Archiving Initiatives
Gomes, D., Miranda, J., & Costa, M. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24469-8_41 · Cited by 104
Masanés, J. (2006) · Cited by 103
Learning to rank for freshness and relevance
Dai, N., Shokouhi, M., & Davison, B. D. (2011) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2009916.2009933 · Cited by 101
Dating Historical Color Images
Palermo, F., Hays, J. H., & Efros, A. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33783-3_36 · Cited by 96
A Language Modeling Approach for Temporal Information Needs
Berberich, K., Bedathur, S., Alonso, O., & Weikum, G. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-12275-0_5 · Cited by 96
Extracting significant time varying features from text
Swan, R. C., & Allan, J. (1999) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/319950.319956 · Cited by 96
A time machine for text search
Berberich, K., Bedathur, S., Neumann, T., & Weikum, G. (2007) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1277741.1277831 · Cited by 95
Time-sensitive query auto-completion
Shokouhi, M., & Radinsky, K. (2012) · Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/2348283.2348364 · Cited by 95
Answering General Time-Sensitive Queries
Dakka, W., Gravano, L., & Ipeirotis, P. G. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2010.187 · Cited by 95
Understanding temporal query dynamics
Kulkarni, A., Teevan, J., Svore, K. M., & Dumais, S. T. (2011) · Proceedings of the fourth ACM international conference on Web search and data mining · doi:10.1145/1935826.1935862 · Cited by 94
Improving search relevance for implicitly temporal queries
Metzler, D., Jones, R., Peng, F., & Zhang, R. (2009) · Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1571941.1572085 · Cited by 94
Masanés, J. (2006) · Springer eBooks · doi:10.1007/978-3-540-46332-0 · Cited by 84
Estimation methods for ranking recent information
Efron, M., & Golovchinsky, G. (2011) · Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval · doi:10.1145/2009916.2009984 · Cited by 78
Detecting seasonal queries by time-series analysis
Shokouhi, M. (2011) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2009916.2010104 · Cited by 78
Snodgrass, R., & Ahn, I. (1985) · ACM SIGMOD Record · doi:10.1145/971699.318921 · Cited by 75
Studying how the past is remembered
Yeung, C. A., & Jatowt, A. (2011) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2063576.2063755 · Cited by 74
Self-citationPage quality: in search of an unbiased web ranking
Cho, J., Roy, S., & Adams, R. E. (2005) · Proceedings of the 2005 ACM SIGMOD international conference on Management of data · doi:10.1145/1066157.1066220 · Cited by 69
Click-through prediction for news queries
König, A. C., Gamon, M., & Wu, Q. (2009) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1571941.1572002 · Cited by 65
Karam, G. M. (1994) · ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) · doi:10.1145/186258.187157 · Cited by 61
Ayalon, O., & Toch, E. (2013) · Symposium On Usable Privacy and Security · doi:10.1145/2501604.2501608 · Cited by 57
Timely YAGO: harvesting, querying, and visualizing temporal knowledge from Wikipedia
Wang, Y., Zhu, M., Qu, L., Spaniol, M., & Weikum, G. (2010) · Proceedings of the 13th International Conference on Extending Database Technology · doi:10.1145/1739041.1739130 · Cited by 54
Leveraging temporal dynamics of document content in relevance ranking
Elsas, J. L., & Dumais, S. T. (2010) · Proceedings of the third ACM international conference on Web search and data mining · doi:10.1145/1718487.1718489 · Cited by 54
Loughlin, C. (2009) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir.2009.04936daa.001 · Cited by 53
Strötgen, J., & Gertz, M. (2010) · Proceedings of the VLDB Endowment · doi:10.14778/1920841.1921041 · Cited by 48
Estimating document focus time
Jatowt, A., Yeung, C. A., & Tanaka, K. (2013) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2505515.2505655 · Cited by 48
Self-citationCoupled temporal scoping of relational facts
Talukdar, P. P., Wijaya, D., & Mitchell, T. (2012) · Proceedings of the fifth ACM international conference on Web search and data mining · doi:10.1145/2124295.2124307 · Cited by 46
Bauer, L., Cranor, L. F., Komanduri, S., Mazurek, M. L., Reiter, M. K., Sleeper, M., & Ur, B. (2013) · ACM Workshop on Privacy in the Electronic Society (WPES) · doi:10.1145/2517840.2517859 · Cited by 43
̈s, J. M. (2007) · Cited by 43
Bridging the Terminology Gap in Web Archive Search ∗
Berberich, K., Bedathur, S., Sozio, M., & Weikum, G. (2009) · Cited by 42
Indexing valid time databases via B/sup +/-trees
Nascimento, M. A., & Dunham, M. H. (1999) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/69.824609 · Cited by 42
Time Sensitive Ranking with Application to Publication Search
Li, X., Liu, B., & Yu, P. S. (2008) · Proceedings · doi:10.1109/icdm.2008.155 · Cited by 40
Timelines as summaries of popular scheduled events
Alonso, O., & Shiells, K. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2487788.2488114 · Cited by 38
NEER: An Unsupervised Method for Named Entity Evolution Recognition
Tahmasebi, N., Gossen, G., Kanhabua, N., Holzmann, H., & Risse, T. (2012) · VBN Forskningsportal (Aalborg Universitet) · Cited by 38
Harvesting facts from textual web sources by constrained label propagation
Wang, Y., Yang, B., Qu, L., Spaniol, M., & Weikum, G. (2011) · Proceedings of the 20th ACM international conference on Information and knowledge management · doi:10.1145/2063576.2063698 · Cited by 37
Activity Prediction: A Twitter-based Exploration
Weerkamp, W., & de Rijke, M. (2012) · UvA-DARE (University of Amsterdam) · Cited by 37
Freshness matters: in flowers, food, and web authority
Dai, N., & Davison, B. D. (2010) · Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1835449.1835471 · Cited by 36
SalahEldeen, H. M., & Nelson, M. L. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2487788.2488121 · Cited by 36
Improving Temporal Language Models for Determining Time of Non-timestamped Documents
Kanhabua, N., & Nørvåg, K. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-87599-4_37 · Cited by 35
Identification of top relevant temporal expressions in documents
Strötgen, J., Alonso, O., & Gertz, M. (2012) · doi:10.1145/2169095.2169102 · Cited by 35
Determining Time of Queries for Re-ranking Search Results
Kanhabua, N., & Nørvåg, K. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15464-5_27 · Cited by 34
Huet, T., Biega, J., & Suchanek, F. M. (2013) · Automated Knowledge Base Construction · doi:10.1145/2509558.2509567 · Cited by 33
Berberich, K., Vazirgiannis, M., & Weikum, G. (2005) · Internet Mathematics · doi:10.1080/15427951.2005.10129110 · Cited by 32
Index maintenance for time-travel text search
Anand, A., Bedathur, S., Berberich, K., & Schenkel, R. (2012) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2348283.2348318 · Cited by 32
Extraction of temporal facts and events from Wikipedia
Kuzey, E., & Weikum, G. (2012) · Proceedings of the 2nd Temporal Web Analytics Workshop · doi:10.1145/2169095.2169101 · Cited by 32
Temporal Evolution of the UK Web
Bordino, I., Boldi, P., Donato, D., Santini, M., & Vigna, S. (2008) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2008.88 · Cited by 30
Joho, H., Jatowt, A., & Blanco, R. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2579044 · Cited by 29
Self-citationHoffmann, L. (2013) · Communications of the ACM · doi:10.1145/2436256.2436263 · Cited by 28
Extracting collective expectations about the future from large text collections
Jatowt, A., & Au Yeung, C.-M. (2011) · Proceedings of the 20th ACM international conference on Information and knowledge management · doi:10.1145/2063576.2063759 · Cited by 28
Self-citationLearning Recurrent Event Queries for Web Search
Zhang, R., Konda, Y., Dong, A., Kolari, P., Chang, Y., & Zheng, Z. (2010) · Cited by 26
Learning to rank search results for time-sensitive queries
Kanhabua, N., & Nørvåg, K. (2012) · Proceedings of the 21st ACM international conference on Information and knowledge management · doi:10.1145/2396761.2398667 · Cited by 26
Analyzing temporal characteristics of check-in data
Bannur, S. N., & Alonso, O. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2579041 · Cited by 25
Aji, A., Wang, Y., Agichtein, E., & Gabrilovich, E. (2010) · Proceedings of the 19th ACM international conference on Information and knowledge management · doi:10.1145/1871437.1871519 · Cited by 24
Ranking related news predictions
Kanhabua, N., Blanco, R., & Matthews, M. (2011) · Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval · doi:10.1145/2009916.2010018 · Cited by 24
Whiting, S., Jose, J. M., & Alonso, O. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2579048 · Cited by 24
Temporal Diversification of Search Results
Berberich, K., & Bedathur, S. (2013) · Max Planck Digital Library · Cited by 23
Web Structure, Dynamics and Page Quality
Baeza-Yates, R., Saint-Jean, F., & Castillo, C. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45735-6_12 · Cited by 23
From Temporal Expressions to Temporal Information: Semantic Tagging of News Messages
Schilder, F., & Habel, C. U. (2005) · Oxford University Press eBooks · doi:10.1093/oso/9780199268535.003.0030 · Cited by 23
Disambiguating Implicit Temporal Queries by Clustering Top Relevant Dates in Web Snippets
Campos, R., Jorge, A., Dias, G. H., & Nunes, C. (2012) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2012.158 · Cited by 23
Self-citationChronoSeeker: search engine for future and past events
Kawai, H., Jatowt, A., Tanaka, K., Kunieda, K., & Yamada, K. (2010) · Proceedings of the 4th International Conference on Uniquitous Information Management and Communication · doi:10.1145/2108616.2108647 · Cited by 22
Self-citationSupporting analysis of future-related information in news archives and the web
Jatowt, A., Kanazawa, K., Oyama, S., & Tanaka, K. (2009) · Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries · doi:10.1145/1555400.1555420 · Cited by 21
Self-citationPasca, M. (2008) · Proceedings of the 2008 ACM symposium on Applied computing · doi:10.1145/1363686.1363946 · Cited by 21
What's really new on the web?: identifying new pages from a series of unstable web snapshots
Toyoda, M., & Kitsuregawa, M. (2006) · Proceedings of the 15th international conference on World Wide Web · doi:10.1145/1135777.1135815 · Cited by 21
What is the Temporal Value of Web Snippets
Campos, R., Dias, G. H., & Jorge, A. (2011) · Cited by 21
Self-citationJatowt, A., Kawai, Y., & Tanaka, K. (2007) · Proceedings of the 9th annual ACM international workshop on Web information and data management · doi:10.1145/1316902.1316925 · Cited by 20
Self-citationA survey of temporal web search experience
Joho, H., Jatowt, A., & Roi, B. (2013) · Proceedings of the 22nd International Conference on World Wide Web · doi:10.1145/2487788.2488126 · Cited by 19
Self-citationTweet classification based on their lifetime duration
Takemura, H., & Tajima, K. (2012) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2396761.2398642 · Cited by 19
Campos, R., Dias, G. H., Jorge, A., & Nunes, C. (2012) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2396761.2398567 · Cited by 19
Self-citationYour two weeks of fame and your grandmother's
Cook, J., Sarma, A. D., Fabrikant, A., & Tomkins, A. (2012) · International World Wide Web Conference (WWW) · doi:10.1145/2187836.2187959 · Cited by 19
Temporal web dynamics and its application to information retrieval
Radinsky, K., Díaz, F., Dumais, S., Shokouhi, M., Dong, A., & Chang, Y. (2013) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2433396.2433500 · Cited by 19
FluxCapacitor: efficient time-travel text search
Berberich, K., Bedathur, S., Neumann, T., & Weikum, G. (2007) · Cited by 17
Time-sensitive web image ranking and retrieval via dynamic multi-task regression
Kim, G., & Xing, E. P. (2013) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2433396.2433417 · Cited by 17
Using neighbors to date web documents
Nunes, S., Ribeiro, C., & David, G. (2007) · Proceedings of the 9th annual ACM international workshop on Web information and data management · doi:10.1145/1316902.1316924 · Cited by 17
Clustering of search results using temporal attributes
Alonso, O., & Gertz, M. (2006) · Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1148170.1148273 · Cited by 17
Evaluating methods to rediscover missing web pages from the web infrastructure
Klein, M., & Nelson, M. L. (2010) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/1816123.1816133 · Cited by 16
TISE: A Temporal Search Engine for Web Contents
Jin, P., Lian, J., Zhao, X., & Wan, S. (2008) · 2008 Second International Symposium on Intelligent Information Technology Application · doi:10.1109/iita.2008.132 · Cited by 15
Creating a billion-scale searchable web archive
Gomes, D., Costa, M. A., Cruz, D., Miranda, J., & Fontes, S. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2487788.2488118 · Cited by 14
Yamamoto, Y., Tezuka, T., Jatowt, A., & Tanaka, K. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-72524-4_28 · Cited by 14
Self-citationRecency ranking by diversification of result set
Styskin, A., Romanenko, F., Vorobyev, F., & Serdyukov, P. (2011) · Proceedings of the 20th ACM international conference on Information and knowledge management · doi:10.1145/2063576.2063862 · Cited by 14
Enhancing Document Snippets Using Temporal Information
Alonso, O., Gertz, M., & Baeza-Yates, R. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24583-1_4 · Cited by 12
Panel on use of proprietary data
Callan, J., & Moffat, A. (2012) · ACM SIGIR Forum · doi:10.1145/2422256.2422258 · Cited by 12
A temporally adaptive content-based relevance ranking algorithm
Perkiö, J., Buntine, W., & Tirri, H. (2005) · Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/1076034.1076171 · Cited by 12
Using Web Snippets and Web Query-logs to Measure Implicit Temporal Intents in Queries
Campos, R., Alípio, M. J., & Dias, G. H. (2011) · HAL · Cited by 12
Self-citationA.: Future retrieval: What does the future talk about
Dias, G. H., Campos, R., & Jorge, A. (2011) · Cited by 12
Self-citationWhen Was It Written? Automatically Determining Publication Dates
Garcia-Fernandez, A., Ligozat, A.-L., Dinarelli, M., & Bernhard, D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24583-1_22 · Cited by 11
Search result re-ranking by feedback control adjustment for time-sensitive query
Zhang, R., Chang, Y., Zheng, Z., Metzler, D., & Nie, J.-Y. (2009) · Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers on - NAACL '09 · doi:10.3115/1620853.1620899 · Cited by 11
How fresh do you want your search results?
Cheng, S., Arvanitis, A., & Hristidis, V. (2013) · Proceedings of the 22nd ACM international conference on Information & Knowledge Management · doi:10.1145/2505515.2505696 · Cited by 11
Improving Retrieval of Future-Related Information in Text Collections
Kanazawa, K., Jatowt, A., & Tanaka, K. (2011) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2011.250 · Cited by 11
Self-citationDias, G. H., Moreno, J. G., Jatowt, A., & Campos, R. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34109-0_21 · Cited by 10
Self-citationHandling temporal information in web search engines
Manica, E., Dorneles, C. F., & Renata Galante, R. (2012) · ACM SIGMOD Record · doi:10.1145/2380776.2380780 · Cited by 10
Archiving Temporal Web Information: Organization of Web Contents for Fast Access and Compact Storage
Song, S., & JáJá, J. F. (2008) · Cited by 9
Utilizing Temporal Information in Topic Detection and Tracking
Makkonen, J., & Ahonen-Myka, H. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-45175-4_36 · Cited by 9
Multi-lingual Analysis of Future-Related Information on the Web
Jatowt, A., Kawai, H. D., Kanazawa, K., Tanaka, K., Kunieda, K., & Yamada, K. (2013) · International Conference on Culture and Computing · doi:10.1109/culturecomputing.2013.13 · Cited by 9
Self-citationTime-Aware Exploratory Search: Exploring Word Meaning through Time
Odijk, D., Santucci, G., de Rijke, M., Angelini, M., & Granato, G. (2012) · UvA-DARE (University of Amsterdam) · Cited by 9
SalahEldeen, H. M., & Nelson, M. L. (2013) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/2467696.2467721 · Cited by 8
Exploring Entity Associations Over Time
Reinanda, R., Odijk, D., & de Rijke, M. (2013) · Data Archiving and Networked Services (DANS) · Cited by 8
Extracting and aggregating temporal events from text
Döhling, L., & Leser, U. (2014) · International World Wide Web Conference (WWW) · doi:10.1145/2567948.2579043 · Cited by 7
Learning-based time-sensitive re-ranking for web search
Chang, P.-T., Huang, Y.-C., Yang, C.-L., Lin, S.-D., & Cheng, P. (2012) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2348283.2348489 · Cited by 7
Analyzing collective view of future, time-referenced events on the web
Jatowt, A., Kawai, H., Kanazawa, K., Tanaka, K., Kunieda, K., & Yamada, K. (2010) · Proceedings of the 19th international conference on World wide web · doi:10.1145/1772690.1772835 · Cited by 7
Self-citationSession Based Click Features for Recency Ranking
Inagaki, Y., Sadagopan, N., Dupret, G., Dong, A., Liao, C., Chang, Y., & Zheng, Z. (2010) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v24i1.7517 · Cited by 7
Temporal Semantics Extraction for Improving Web Search
Vicente-Diez, M. T., & Martinez, P. (2009) · 2009 20th International Workshop on Database and Expert Systems Application · doi:10.1109/dexa.2009.57 · Cited by 7
Events Retrieval Using Enhanced Semantic Web Knowledge
Vandenbussche, P.-Y., & Teissèdre, C. (2011) · HAL · Cited by 7
Jatowt, A., Kawai, Y., & Tanaka, K. (2011) · ACM Symposium on Applied Computing · doi:10.1145/1982185.1982437 · Cited by 6
Self-citationCreating temporally dynamic web search snippets
Svore, K. M., Teevan, J., Dumais, S. T., & Kulkarni, A. (2012) · Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/2348283.2348461 · Cited by 6
Proximity 2 -aware ranking for textual, temporal, and geographic queries
Strötgen, J., & Gertz, M. (2013) · Proceedings of the 22nd ACM international conference on Information & Knowledge Management · doi:10.1145/2505515.2505640 · Cited by 5
Recovering a website's server components from the web infrastructure
McCown, F., & Nelson, M. L. (2008) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/1378889.1378911 · Cited by 5
Campos, R., Dias, G. H., & Jorge, A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24769-9_42 · Cited by 5
Self-citationHashtags as Milestones in Time
Whiting, S., & Alonso, O. (2012) · Cited by 5
GTE-Cluster: A Temporal Search Interface for Implicit Temporal Queries
Campos, R., Dias, G., Jorge, A. M., & Nunes, C. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-06028-6_94 · Cited by 2
Self-citationProcessing Temporal Information in Unstructured Documents
Ciências, F. D. (2012) · Cited by 2
Annotating Events and Temporal Information in Newswire Texts
Setzer, A., & Gaizauskas, R. (2000) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/3t5qg4pxtf8i · Cited by 1
(2003)
(2005) · University of Twente Research Information
(2009)
(2012)
(2013) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
(2012) · International Conference on Computational Linguistics
Flagged first, then by citations
7 of the 166 references couldn’t be matched to a known paper.
Research works printed but not linked: 19
- Advanced Research Projects Agency . 1993 . Software and intelligent systems technology office . In Proceedings of the 5th Conference on Message Understanding. Morgan Kaufmann. Advanced Research Projects Agency. 1993. Software and intelligent systems technology office. In Proceedings of the 5th Conference on Message Understanding. Morgan Kaufmann.
- O. Alonso , R. Baeza-Yates , and M. Gertz . 2007a. Exploratory search using timelines . In Proceedings of the Workshop on Exploratory Search and Computer Human Interaction Associated to CHI'07: SIGCHI. ACM. O. Alonso, R. Baeza-Yates, and M. Gertz. 2007a. Exploratory search using timelines. In Proceedings of the Workshop on Exploratory Search and Computer Human Interaction Associated to CHI'07: SIGCHI. ACM.
- O. Alonso , R. Baeza-Yates , and M. Gertz . 2009b. Effectiveness of temporal snippets . In Proceedings of the WSRSP'09 Workshop associated to WWW'09 . ACM. O. Alonso, R. Baeza-Yates, and M. Gertz. 2009b. Effectiveness of temporal snippets. In Proceedings of the WSRSP'09 Workshop associated to WWW'09. ACM.
- R. Baeza-Yates . 2005 . Searching the future . In Proceedings of the Mathematical/Formal Methods in Information Retrieval Workshop Associated to SIGIR'05 . ACM. R. Baeza-Yates. 2005. Searching the future. In Proceedings of the Mathematical/Formal Methods in Information Retrieval Workshop Associated to SIGIR'05. ACM.
- K. Bollacker , P. Tufts , T. Pierce , and R. Cook . 2007. A platform for scalable, collaborative, structured information integration . In Proceedings of the IIWeb'07 Workshop Associated to AAAI'07 . AAAI Press, 22--27. K. Bollacker, P. Tufts, T. Pierce, and R. Cook. 2007. A platform for scalable, collaborative, structured information integration. In Proceedings of the IIWeb'07 Workshop Associated to AAAI'07. AAAI Press, 22--27.
- 10.5555/297805.297827 · DOI
- H. Cunningham , D. Maynard , K. Bontcheva , and V. Tablan . 2002. GATE: A framework and graphical development environment for robust NLP tools and applications . In Proceedings of ACL'02 . Association for Computational Linguistics, 168--175. H. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. 2002. GATE: A framework and graphical development environment for robust NLP tools and applications. In Proceedings of ACL'02. Association for Computational Linguistics, 168--175.
- M. Efron . 2012 . Query-specific recency ranking: Survival analysis for improved microblog retrieval . In Proceedings of the TAIA'12 Workshop associated to SIGIR'12 . M. Efron. 2012. Query-specific recency ranking: Survival analysis for improved microblog retrieval. In Proceedings of the TAIA'12 Workshop associated to SIGIR'12.
- N. Kanhabua , C. Niederee , and W. Siberski . 2013. Towards concise preservation by managed forgetting: Research issues and case study . In Proceedings of the iPRES'13 . N. Kanhabua, C. Niederee, and W. Siberski. 2013. Towards concise preservation by managed forgetting: Research issues and case study. In Proceedings of the iPRES'13.
- H. Li , G. Xu , W. B. Croft , M. Bendersky , Z. Wang , and E. Viegas . 2012. A public dataset for promoting query representation and understanding research . In Proceedings of the WSCD'12 . H. Li, G. Xu, W. B. Croft, M. Bendersky, Z. Wang, and E. Viegas. 2012. A public dataset for promoting query representation and understanding research. In Proceedings of the WSCD'12.
- M. Matthews , P. Tolchinsky , R. Blanco , J. Atserias , P. Mika , and H. Zaragoza . 2010. Searching through time in the New York Times . In Proceedings of the HCIR'10 Workshop. 41--44 . M. Matthews, P. Tolchinsky, R. Blanco, J. Atserias, P. Mika, and H. Zaragoza. 2010. Searching through time in the New York Times. In Proceedings of the HCIR'10 Workshop. 41--44.
- 10.1002/asi.v58:13 · DOI
- S. Nunes , C. Ribeiro , and G. David . 2008. Use of temporal expressions in web search . In Proceedings of the ECIR'08 . Springer-Verlag. 580--584. S. Nunes, C. Ribeiro, and G. David. 2008. Use of temporal expressions in web search. In Proceedings of the ECIR'08. Springer-Verlag. 580--584.
- D. Odijk , G. Santucci , M. de Rijke , M. Angelini , and G. Granato . 2012. Exploring word meaning through time . In Proceedings of the TAIA'12 Workshop Associated to SIGIR'12 . D. Odijk, G. Santucci, M. de Rijke, M. Angelini, and G. Granato. 2012. Exploring word meaning through time. In Proceedings of the TAIA'12 Workshop Associated to SIGIR'12.
- M. Osborne , S. Petrovic , R. McCreadie , C. Macdonald , and I. Ounis . 2012. Bieber no more: First story detection using Twitter and Wikipedia . In Proceedings of the TAIA'12 Workshop Associated to SIGIR'12 . M. Osborne, S. Petrovic, R. McCreadie, C. Macdonald, and I. Ounis. 2012. Bieber no more: First story detection using Twitter and Wikipedia. In Proceedings of the TAIA'12 Workshop Associated to SIGIR'12.
- J. Pustejovsky , M. Verhagen , R. Sauri , J. Littman , R. J. Gaizauskas , G. Katz , I. Mani , R. Knippen , and A. Setzer . 2006. TimeBank 1.2 . In Proceedings of the Linguistic Data Consortium. J. Pustejovsky, M. Verhagen, R. Sauri, J. Littman, R. J. Gaizauskas, G. Katz, I. Mani, R. Knippen, and A. Setzer. 2006. TimeBank 1.2. In Proceedings of the Linguistic Data Consortium.
- B. Shaparenko , R. Caruana , J. Gehrke , and T. Joachims . 2005. Identifying temporal patterns and key players in document collections . In Proceedings of the TDM'05 Workshop Associated to ICDM'05 . IEEE Computer Society Press, 165--174. B. Shaparenko, R. Caruana, J. Gehrke, and T. Joachims. 2005. Identifying temporal patterns and key players in document collections. In Proceedings of the TDM'05 Workshop Associated to ICDM'05. IEEE Computer Society Press, 165--174.
- 10.1145/318898.318921 · DOI
- 10.5555/1620853.1620899 · DOI
Cited by
Sorted by citations
Current Challenges and Future Research Areas for Digital Forensic InvestigationPreprint
Lillis, D., Becker, B. A., O’Sullivan, T., & Scanlon, M. (2016) · arXiv (Cornell University) · doi:10.13140/rg.2.2.34898.76489 · Cited by 185
Complex Temporal Question Answering on Knowledge Graphs
Jia, Z., Pramanik, S., Roy, R. S., & Weikum, G. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482416 · Cited by 136
Clustering With Outlier Removal
Liu, H., Li, J., Wu, Y., & Fu, Y. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2954317 · Cited by 112
(2024) · ACM eBooks · doi:10.1145/3674127 · Cited by 86
Time Masking for Temporal Language Models
Rosin, G. D., Guy, I., & Radinsky, K. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498529 · Cited by 81
Liu, J., Chen, Y., & Liu, K. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016754 · Cited by 72
RDF dataset profiling – a survey of features, methods, vocabularies and applications
Ellefi, M. B., Bellahsène, Z., Breslin, J. G., Demidova, E., Dietze, S., Szymański, J., & Todorov, K. (2018) · Semantic Web · doi:10.3233/sw-180294 · Cited by 69
Time Expression Analysis and Recognition Using Syntactic Token Types and General Heuristic Rules
Zhong, X., Sun, A., & Cambria, E. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1039 · Cited by 68
A Baseline Temporal Tagger for all Languages
Strötgen, J., & Gertz, M. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1063 · Cited by 66
A survey on narrative extraction from textual data
Santana, B. S., Campos, R., de Amorim, E. C. F., Jorge, A., Silvano, P., & Nunes, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10338-7 · Cited by 66
Self-citationA Survey of Modelling Trends in Temporal GIS
Siabato, W., Claramunt, C., Ilarri, S., & Callejo, M. Á. M. (2018) · ACM Computing Surveys · doi:10.1145/3141772 · Cited by 55
A survey of recent methods on deriving topics from Twitter: algorithm to evaluation
Nugroho, R. S. A., Paris, C. L., Nepal, ., Yang, J. Y., & Zhao, W. (2020) · Knowledge and Information Systems · doi:10.1007/s10115-019-01429-z · Cited by 49
Extracting Time Expressions and Named Entities with Constituent-Based Tagging Schemes
Zhong, X., Cambria, E., & Hussain, A. (2020) · Cognitive Computation · doi:10.1007/s12559-020-09714-8 · Cited by 45
BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information
Wang, J., Jatowt, A., Yoshikawa, M., & Cai, Y. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591686 · Cited by 44
Self-citationThe Past is Not a Foreign Country: Detecting Semantically Similar Terms across Time
Zhang, Y., Jatowt, A., Bhowmick, S. S., & Tanaka, K. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2591008 · Cited by 44
Self-citationTemporal Information Retrieval
Kanhabua, N., & Anand, A. (2016) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2911451.2914805 · Cited by 38
Temporal Blind Spots in Large Language Models
Wallat, J., Jatowt, A., & Anand, A. (2024) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3616855.3635818 · Cited by 37
Self-citationTime Expression Recognition Using a Constituent-based Tagging Scheme
Zhong, X., & Cambria, E. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3185997 · Cited by 37
A Survey on Temporal Reasoning for Temporal Information Extraction from Text
Leeuwenberg, A., & Moens, M. (2019) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11727 · Cited by 37
Spitz, A., & Gertz, M. (2016) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2911451.2911529 · Cited by 36
Time expression recognition and normalization: a survey
Zhong, X., & Cambria, E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10400-y · Cited by 33
Temporal information searching behaviour and strategies
Joho, H., Jatowt, A., & Blanco, R. (2015) · Information Processing & Management · doi:10.1016/j.ipm.2015.03.006 · Cited by 33
Self-citationSeasonal Relevance in E-Commerce Search
Yang, H., Gupta, P., Galán, R. F., Bu, D., & Jia, D. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3481951 · Cited by 32
Singh, J., Nejdl, W., & Anand, A. (2016) · Conference on Human Information Interaction and Retrieval · doi:10.1145/2854946.2854959 · Cited by 32
Treating Cold Start in Product Search by Priors
Gupta, P., Dreossi, T., Bakus, J., Lin, Y.-H., & Salaka, V. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366424.3382705 · Cited by 31
Time-Aware Boolean Spatial Keyword Queries
Chen, G., Zhao, J., Gao, Y., Chen, L., & Chen, R. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2742956 · Cited by 31
Jatowt, A., Antoine, É., Kawai, Y., & Akiyama, T. (2015) · International World Wide Web Conference (WWW) · doi:10.1145/2736277.2741632 · Cited by 29
Self-citationTempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions
Abdallah, A., Piryani, B., Wallat, J., Anand, A., & Jatowt, A. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3773966.3777938 · Cited by 28
Self-citationExploring Web Archives Through Temporal Anchor Texts
Holzmann, H., Nejdl, W., & Anand, A. (2017) · ACM Web Science Conference (WebSci) · doi:10.1145/3091478.3091500 · Cited by 28
Wang, J., Jatowt, A., & Yoshikawa, M. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531734 · Cited by 28
Self-citationDomain-Sensitive Temporal Tagging
Strötgen, J., & Gertz, M. (2016) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-02163-3 · Cited by 26
Holzmann, H., & Anand, A. (2016) · International World Wide Web Conference (WWW) · doi:10.1145/2872518.2890555 · Cited by 26
History by Diversity: Helping Historians search News ArchivesPreprint
Singh, J., Nejdl, W., & Anand, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10251 · Cited by 26
Rogers, R., Gomes, D., Demidova, E., Winters, J., & Risse, T. (2021) · Springer eBooks · doi:10.1007/978-3-030-63291-5 · Cited by 24
Towards Efficient Framework for Time-Aware Spatial Keyword Queries on Road Networks
Zhao, J., Gao, Y., Chen, G., & Chen, R. (2017) · ACM Transactions on Information Systems · doi:10.1145/3143802 · Cited by 23
Ranking Models for the Temporal Dimension of Text
Rizzo, S., Brucato, M., & Montesi, D. (2022) · ACM Transactions on Information Systems · doi:10.1145/3565481 · Cited by 22
Singh, J., Nejdl, W., & Anand, A. (2016) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2911451.2911465 · Cited by 22
Towards Ontological Approach on Trust-Aware Ambient Services
Lee, O., Nguyễn, H. L., Jung, J. E., Um, T., & Lee, H. (2017) · IEEE Access · doi:10.1109/access.2017.2663407 · Cited by 22
Across-Time Comparative Summarization of News Articles
Duan, Y., & Jatowt, A. (2019) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3289600.3291008 · Cited by 21
Self-citationImproving question answering for event-focused questions in temporal collections of news articles
Wang, J., Jatowt, A., Färber, M., & Yoshikawa, M. (2021) · Information Retrieval · doi:10.1007/s10791-020-09387-9 · Cited by 21
Self-citationTISCO: Temporal scoping of facts
Rula, A., Palmonari, M., Rubinacci, S., Ngomo, A.-C. N., Lehmann, J., Maurino, A., & Esteves, D. (2018) · Journal of Web Semantics · doi:10.1016/j.websem.2018.09.002 · Cited by 20
When time meets information retrieval: Past proposals, current plans and future trends
Moulahi, B., Tamine, L., & Yahia, S. B. (2015) · Journal of Information Science · doi:10.1177/0165551515607277 · Cited by 20
Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
Fang, H., Tao, S., Chen, N., Chang, K.-X., & Sakai, T. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769493 · Cited by 19
Identifying top relevant dates for implicit time sensitive queries
Campos, R., Dias, G. H., Jorge, A., & Nunes, C. (2017) · Information Retrieval · doi:10.1007/s10791-017-9302-1 · Cited by 18
Self-citationQiu, Q., Huang, Z., Xu, D., Ma, K., Tao, L., Wang, R., Chen, J., Xie, Z., & Pan, Y. (2023) · Journal of Earth Science · doi:10.1007/s12583-022-1716-z · Cited by 17
Quantifying retrieval bias in Web archive search
Samar, T., Traub, M. C., van Ossenbruggen, J., Hardman, L., & de Vries, A. P. (2017) · International Journal on Digital Libraries · doi:10.1007/s00799-017-0215-9 · Cited by 17
Towards Extracting Absolute Event Timelines From English Clinical Reports
Leeuwenberg, A., & Moens, M. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3027201 · Cited by 17
Identifying temporality of word senses based on minimum cuts
Hasanuzzaman, M., Dias, G. H., Ferrari, S., Mathet, Y., & Way, A. (2016) · Dublin City University Open Access Institutional Repository (Dublin City University) · doi:10.18653/v1/k16-2
Domain-Sensitive Temporal Tagging
Strötgen, J., & Gertz, M. (2016) · Synthesis lectures on human language technologies · doi:10.2200/s00721ed1v01y201606hlt036 · Cited by 16
Analyzing history-related posts in twitter
Sumikawa, Y., & Jatowt, A. (2020) · International Journal on Digital Libraries · doi:10.1007/s00799-020-00296-2 · Cited by 16
Self-citationDigital History meets Microblogging
Sumikawa, Y., Jatowt, A., & Düring, M. (2018) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3197026.3197057 · Cited by 16
Self-citationGTE-Rank: A time-aware search engine to answer time-sensitive queries
Campos, R., Dias, G. H., Jorge, A., & Nunes, C. (2015) · Information Processing & Management · doi:10.1016/j.ipm.2015.07.006 · Cited by 15
Self-citationExtraction of spatio‐temporal data about historical events from text documents
Abraham, S., Mäs, S., & Bernard, L. (2018) · Transactions in GIS · doi:10.1111/tgis.12448 · Cited by 15
Assessing Query Translation Quality Using Back Translation in Hindi-English CLIR
Chandra, G., & Dwivedi, S. K. (2017) · International Journal of Intelligent Systems and Applications · doi:10.5815/ijisa.2017.03.07 · Cited by 15
Time and information retrieval: Introduction to the special issue
Derczynski, L., Strötgen, J., Campos, R., & Alonso, O. (2015) · Information Processing & Management · doi:10.1016/j.ipm.2015.05.002 · Cited by 15
Self-citationUser Interface Evaluation on Government Knowledge Management Portal Using Webqual 4.0
Maryani, M., Mahesworo, B., Perbangsa, A. S., & Hendarti, H. (2019) · International Conference on Information Management and Technology (ICIMTech) · doi:10.1109/icimtech.2019.8843780 · Cited by 14
Irregular Indeterminate Repeated Facts in Temporal Relational Databases
Paolo Terenziani, B. (2015) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2015.2509976 · Cited by 14
Generic method for detecting focus time of documents
Jatowt, A., Yeung, C. M. A., & Tanaka, K. (2015) · Information Processing & Management · doi:10.1016/j.ipm.2015.05.001 · Cited by 14
Self-citationTemporal validity reassessment: commonsense reasoning about information obsoleteness
Hosokawa, T., Jatowt, A., & Sugiyama, K. (2024) · Discover Computing · doi:10.1007/s10791-024-09433-w · Cited by 13
Self-citationTemporal knowledge extraction from large-scale text corpus
Liu, Y., Hua, W., & Zhou, X. (2020) · World Wide Web · doi:10.1007/s11280-020-00836-5 · Cited by 13
Diversifying Search Results Using Time
Gupta, D., & Berberich, K. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-30671-1_69 · Cited by 12
Enhancing Cross-Modal Retrieval Based on Modality-Specific and Embedding Spaces
Yanagi, R., Togo, R., Ogawa, T., & Haseyama, M. (2020) · IEEE Access · doi:10.1109/access.2020.2995815 · Cited by 12
Wang, J., Jatowt, A., & Yoshikawa, M. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462885 · Cited by 12
Self-citationSelective dissemination of information (SDI) in the age of artificial intelligence (AI)
majd, H. S., Saeidnia, H. R., Ausloos, M., & Hassanzadeh, M. (2023) · Library Hi Tech News · doi:10.1108/lhtn-08-2023-0156 · Cited by 12
Leveraging Semantic Annotations to Link Wikipedia and News Archives
Mishra, A., & Berberich, K. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-30671-1_3 · Cited by 12
Extending an Information Retrieval System through Time Event Extraction.
Basile, P., Caputo, A., Semeraro, G. M., & Siciliani, L. (2014) · Cited by 12
Section-Based Focus Time Estimation of News Articles
Khan, S. U. R., Islam, M. A., Aleem, M., Iqbal, M. A., & Ahmed, U. (2018) · IEEE Access · doi:10.1109/access.2018.2882988 · Cited by 12
Kuzey, E., Strötgen, J., Setty, V., & Weikum, G. (2016) · International World Wide Web Conference (WWW) · doi:10.1145/2872518.2889289 · Cited by 11
On the Applicability of Delicious for Temporal Search on Web Archives
Holzmann, H., Nejdl, W., & Anand, A. (2016) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2911451.2914724 · Cited by 11
Modeling the Influence of Popular Trending Events on User Search Behavior
Santu, S. K. K., Li, L., Park, D. H., Chang, Y., & Zhai, C. (2017) · International World Wide Web Conference (WWW) · doi:10.1145/3041021.3054188 · Cited by 11
Constructing a Comprehensive Events Database from the Web
Wang, Q., Kanagal, B., Garg, V. K., & Sivakumar, D. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357986 · Cited by 11
Tang, J., Lu, X., Xiang, Y., Shi, C., & Gu, J. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.08.008 · Cited by 11
Answering Event-Related Questions over Long-Term News Article Archives
Wang, J., Jatowt, A., Färber, M., & Yoshikawa, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_51 · Cited by 11
Self-citationQuery expansion based on clustering and personalized information retrieval
Khalifi, H., Cherif, W., Qadi, A. E., & Ghanou, Y. (2019) · Progress in Artificial Intelligence · doi:10.1007/s13748-019-00178-y · Cited by 10
Rosin, G. D., Guy, I., & Radinsky, K. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441833 · Cited by 10
Content and link-structure perspective of ranking webpages: A review
Ali, F., & Khusro, S. (2021) · Computer Science Review · doi:10.1016/j.cosrev.2021.100397 · Cited by 10
Automatic Generation of Timelines for Past-Web Events
Campos, R., Pasquali, A., Jatowt, A., Mangaravite, V., & Jorge, A. (2021) · Springer eBooks · doi:10.1007/978-3-030-63291-5_18 · Cited by 10
Self-citationEfficient time-interval augmented spatial keyword queries on road networks
Luo, C., Wang, P., Li, Y., Zheng, B., & Li, G. (2022) · Information Sciences · doi:10.1016/j.ins.2022.01.066 · Cited by 10
Language Technologies for the Challenges of the Digital Age
Rehm, G., & Declerck, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73706-5 · Cited by 10
Yan, L., Zhao, P., & Ma, Z. (2019) · Computing · doi:10.1007/s00607-019-00703-w · Cited by 10
An Overview Of Temporal Commonsense Reasoning and AcquisitionPreprint
Wenzel, G., & Jatowt, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.00002 · Cited by 10
Self-citationCastells, P., & Jannach, D. (2024) · ACM eBooks · doi:10.1145/3674127.3674131 · Cited by 9
Wang, J., Jatowt, A., & Cai, Y. (2025) · ACM Transactions on the Web · doi:10.1145/3723352 · Cited by 9
Self-citationDetecting Seasonal Queries Using Time Series and Content Features
Mansouri, B., Zahedi, M. S., Rahgozar, M., & Campos, R. (2017) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3121050.3121100 · Cited by 9
Self-citationDegaetano‐Ortlieb, S., & Strötgen, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73706-5_22 · Cited by 9
Agarwal, P., & Strötgen, J. (2017) · International World Wide Web Conference (WWW) · doi:10.1145/3041021.3051112 · Cited by 8
Terms in Time and Times in Context
Spitz, A., Strötgen, J., Bögel, T., & Gertz, M. (2015) · International World Wide Web Conference (WWW) · doi:10.1145/2740908.2741693 · Cited by 8
Coverage and diversity aware top-k query for spatio-temporal posts
Mehta, P., Skoutas, D., Sacharidis, D., & Voisard, A. (2016) · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS) · doi:10.1145/2996913.2996941 · Cited by 8
Time expression and named entity analysis and recognition
Zhong, X. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/142924 · Cited by 8
Timestamp Approximate Nearest Neighbor Search Over High-Dimensional Vector Data
Wang, Y.-X., He, Z., Tong, Y., Zhou, Z., & Zhong, Y. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00228 · Cited by 7
Sub-document Timestamping of Web Documents
Zhao, Y., & Hauff, C. (2015) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2766462.2767803 · Cited by 7
Gupta, D., Strötgen, J., & Berberich, K. (2016) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/2970398.2970411 · Cited by 7
Learning Temporal Ambiguity in Web Search Queries
Mansouri, B., Zahedi, M. S., Rahgozar, M., Oroumchian, F., & Campos, R. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3133129 · Cited by 7
Self-citationAccessing web archives from different perspectives with potential synergies
Holzmann, H., & Risse, T. (2017) · doi:10.14296/resaw.0001 · Cited by 7
Voxel modeling and association of ubiquitous spatiotemporal information in natural language texts
Wang, D., Tong, X., Dai, C., Guo, C., Lei, Y., Qiu, C., Li, H., & Sun, Y. (2023) · International Journal of Digital Earth · doi:10.1080/17538947.2023.2185692 · Cited by 6
Unveiling temporal patterns in information for improved rumor detection
Mairaj, O., & Khan, S. U. R. (2025) · Social Network Analysis and Mining · doi:10.1007/s13278-025-01421-2 · Cited by 6
ParsTime: Rule-Based Extraction and Normalization of Persian Temporal Expressions
Mansouri, B., Zahedi, M. S., Campos, R., Farhoodi, M., & Rahgozar, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-76941-7_67 · Cited by 6
Self-citationTowards Content Expiry Date Determination: Predicting Validity Periods of Sentences
Almquist, A., & Jatowt, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15712-8_6 · Cited by 6
Self-citationAlsayyahi, S., & Batista-Navarro, R. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.1016 · Cited by 6
XTime: A general rule-based method for time expression recognition and normalization
Zhong, X., Jin, C., An, M., & Cambria, E. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111921 · Cited by 6
Metadata
- Authors
- Campos, R., Dias, G., Jorge, A. M., & Jatowt, A.
- Affiliations
- University of Beira Interior (PT)
- GREYC (FR)
- LIAAD -- INESC TEC, DCC-FCUP, University of Porto, Porto, Portugal
- Kyoto University (JP)
- Venue
- ACM Computing Surveys
- Published
- 2014-08-25
- Volume
- 47
- Issue
- 2
- Pages
- 1-41
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W2039297031
- Cited by
- 262
- References
- 166
- Citations by year
- 2026: 16 · 2025: 12 · 2024: 30 · 2023: 17 · 2022: 12 · 2021: 23 · 2020: 16 · 2019: 21 · 2018: 25 · 2017: 35 · 2016: 38 · 2015: 15 · 2014: 2
- FWCI
- 51.88
- Type
- journal article
- Language
- en
- Open access
- Locations
- ACM Computing Surveys (publishedVersion)
- Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion, other-oa)
- HAL (submittedVersion)
- Funders
- European Regional Development Fund (ERDF)
- Center of Mathematics, University of Beira Interior, within project PEst-OE/MAT/UI0212/2014
- Project NORTE-07-0124-FEDER-000059
- JST research promotion program Presto
- National Strategic Reference Framework (NSRF)
- MEXT Grant-in-Aid for Young Scientists B (#22700096)
- North Portugal Regional Operational Programme (ON.2 -- O Novo Norte)
- National Funds through the FCT within project FCOMP-01-0124-FEDER-037281
- Portuguese funding agency (FCT)
- ERDF through the COMPETE Programme (operational programme for competitiveness)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Mathematics › Theoretical Computer Science › Algorithms and Data Compression
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- temporal information retrieval, temporal queries, research categorization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
