CoChat

Reading Wikipedia to Answer Open-Domain Questions

Open access
Chen, Danqi, Fisch, Adam, Weston, Jason, Bordes, Antoine · 2017 · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The DOI matches its Crossref record; 34 of the 39 references it cites were found in a registry or an index.

Abstract

This paper proposes to tackle open-domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/p17-1171

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 An overview of our question answering system DrQA.
Figure 1 An overview of our question answering system DrQA.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • Adam: A Method for Stochastic Optimization

    Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×

    “We use Adamax for optimization as described in (Kingma and Ba, 2014).”
    Method
  • Glove: Global Vectors for Word Representation

    Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×

    “The feature vector ˜ p i is comprised of the following parts: We use the 300-dimensional Glove word embeddings trained from 840B Web crawl data (Pennington et al., 2014).”
    Method
  • Neural Machine Translation by Jointly Learning to Align and Translate

    Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 2×

    “…has made considerable progress recently thanks to new deep learning architectures like attention-based and memory-1 augmented neural networks (Bahdanau et al., 2015; Weston et al., 2015; Graves et al., 2014) and release of new training and evaluation datasets like QuizBowl (Iyyer et al., 2014),…”
    Background
  • The Stanford CoreNLP Natural Language Processing Toolkit

    Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., & McClosky, D. (2014) · Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.3115/v1/p14-5010 · Cited by 7,037 · cited 2×

    “We apply the Stanford CoreNLP toolkit (Manning et al., 2014) for tokenization and also generating lemma, part-of-speech, and named entity manual features.”
    Method
  • SQuAD: 100,000+ Questions for Machine Comprehension of Text

    Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 10×

    “Next we evaluate our Document Reader component on the standard SQuAD evaluation (Rajpurkar et al., 2016).”
    BackgroundMethodInfluential
  • A unified architecture for natural language processing: deep neural networks with multitask learning

    Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 1×

    “Multitask learning (Caruana, 1998) and task transfer have a rich history in machine learning (e.g., using ImageNet in the computer vision community (Huh et al., 2016)), as well as in NLP in particular (Collobert and Weston, 2008).”
    MethodSelf-citation
  • Freebase: a collaboratively created graph database for structuring human knowledge

    Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376746 · Cited by 4,852 · cited 11×

    “Unlike knowledge bases (KBs) such as Freebase (Bollacker et al., 2008) or DBPedia (Auer et al.”
    BackgroundMethodInfluential
  • Distant supervision for relation extraction without labeled data

    Mintz, M., Bills, S., Snow, R., & Jurafsky, D. (2009) · Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - ACL-IJCNLP '09 · doi:10.3115/1690219.1690287 · Cited by 2,752 · cited 1×

    “Following previous work on distant supervision (DS) for relation extraction (Mintz et al., 2009), we use a”
    Method
  • Teaching Machines to Read and Comprehend

    Hermann, K. M., Kočiský, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., & Blunsom, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03340 · Cited by 2,521 · cited 7×

    “…Graves et al., 2014) and release of new training and evaluation datasets like QuizBowl (Iyyer et al., 2014), CNN/Daily Mail based on news articles (Hermann et al., 2015), CBT based on children books (Hill et al., 2016), or SQuAD (Rajpurkar et al., 2016) and WikiReading (Hewlett et al., 2016),…”
    BackgroundMethodInfluential
  • 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 · cited 3×

    “Unlike knowledge bases (KBs) such as Freebase (Bollacker et al., 2008) or DB-Pedia (Auer et al., 2007), which are easier for computers to process but too sparsely populated for open-domain question answering (Miller et al., 2016), Wikipedia contains up-to-date knowledge that humans are interested in.”
    Background
  • Semantic Parsing on Freebase from Question-Answer Pairs

    Berant, J., Chou, A., Frostig, R., & Liang, P. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1160 · Cited by 1,517

  • Building Watson: An Overview of the DeepQA Project

    Ferrucci, D., Brown, E., Chu‐Carroll, J., Fan, J., Gondek, D., Kalyanpur, A. A., Lally, A., Murdock, J. W., Nyberg, E., Prager, J., et al. (2010) · AI Magazine · doi:10.1609/aimag.v31i3.2303 · Cited by 1,497 · cited 5×

    “, 2002), IBM’s DeepQA (Ferrucci et al., 2010) and YodaQA (Baudiš, 2015; Baudiš and Šedivỳ, 2015) – the latter of which is open source and hence reproducible for comparison purposes.”
    BackgroundMethodInfluential
  • Bidirectional Attention Flow for Machine Comprehension

    Seo, M. J., Kembhavi, A., Farhadi, A., & Hajishirzi, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01603 · Cited by 1,445

  • Multitask learning

    Caruana, R. (1998) · Cited by 1,110

  • Neural Turing Machines

    Graves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058 · cited 3×

    “That subfield has made considerable progress recently thanks to new deep learning architectures like attention-based and memory-1 augmented neural networks (Bahdanau et al., 2015; Weston et al., 2015; Graves et al., 2014) and release of new training and evaluation datasets like QuizBowl (Iyyer et al., 2014), CNN/Daily…”
    Background
  • Untitled work

    (2016) · doi:10.18653/v1/d16-1147 · Cited by 1,035 · cited 3×

    “WikiMovies This dataset, introduced in (Miller et al., 2016), contains 96k question-answer pairs in the domain of movies.”
    BackgroundInfluentialSelf-citation
  • Feature hashing for large scale multitask learning

    Weinberger, K., Dasgupta, A., Langford, J., Smola, A., & Attenberg, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553516 · Cited by 906 · cited 2×

    “Our best performing system uses bigram counts while preserving speed and memory efficiency by using the hashing of (Weinberger et al., 2009) to map the bigrams to 224 bins with an unsigned murmur3 hash.”
    Method
  • Large-scale Simple Question Answering with Memory Networks

    Bordes, A., Usunier, N., Chopra, S., & Weston, J. (2015) · arXiv · doi:10.48550/arxiv.1506.02075 · Cited by 528 · cited 5×

    “Bordes et al. (2015) combined We-bQuestions and SimpleQuestions using distant supervision with Freebase as the KB to give slight improvements on both datasets, although poor performance was reported when training on only one dataset and testing on the other, showing that task transfer is indeed a…”
    MethodInfluentialSelf-citation
  • A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

    Chen, D., Bolton, J., & Manning, C. D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1223 · Cited by 491 · cited 2×

    “Our Document Reader model is inspired by the recent success of neural network models on machine comprehension tasks, in a similar spirit to the At-tentiveReader described in (Hermann et al., 2015; Chen et al., 2016).”
    MethodSelf-citation
  • The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations

    Hill, F., Bordes, A., Chopra, S., & Weston, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.02301 · Cited by 467 · cited 4×

    “This challenge thus encourages research in the ability of a machine to read, a key motivation for the machine comprehension subfield and the creation of datasets such as SQuAD (Rajpurkar et al., 2016), CNN/Daily Mail (Hermann et al., 2015) and CBT (Hill et al., 2016).”
    BackgroundInfluentialSelf-citation
  • Dynamic Coattention Networks For Question Answering

    Xiong, C., Zhong, V., & Socher, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01604 · Cited by 450 · cited 1×

    “Test EM F1 EM F1 Dynamic Coattention Networks (Xiong et al., 2016) find that while these help for more exact paragraph reading in SQuAD, they don’t improve results in the full setting.”
    Background
  • Open question answering over curated and extracted knowledge bases

    Fader, A., Zettlemoyer, L., & Etzioni, O. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623677 · Cited by 407 · cited 3×

    “Fader et al. (2014) used We-bQuestions, TREC and WikiAnswers with four KBs as knowledge sources and reported improvement on the latter two datasets through multi-task learning.”
    Method
  • An analysis of the AskMSR question-answering system

    Brill, E., Dumais, S., & Banko, M. (2002) · Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02 · doi:10.3115/1118693.1118726 · Cited by 313 · cited 3×

    “There are a number of highly developed full pipeline QA approaches using either the Web, as does QuASE (Sun et al., 2015), or Wikipedia as a resource, as do Microsoft’s AskMSR (Brill et al., 2002), IBM’s DeepQA (Ferrucci et al., 2010) and YodaQA (Baudi ˇ s, 2015; Baudi ˇ s and ˇSediv ` y, 2015) — the latter of which i…”
    Method
  • A Neural Network for Factoid Question Answering over Paragraphs

    Iyyer, M., Boyd-Graber, J., Claudino, L., Socher, R., & Daumé III, H. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1070 · Cited by 301 · cited 3×

    “That subfield has made considerable progress recently thanks to new deep learning architectures like attention-based and memory-1 augmented neural networks (Bahdanau et al., 2015; Weston et al., 2015; Graves et al., 2014) and release of new training and evaluation datasets like QuizBowl (Iyyer et al., 2014), CNN/Daily…”
    Background
  • What makes ImageNet good for transfer learning?

    Huh, M., Agrawal, P., & Efros, A. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.08614 · Cited by 266 · cited 2×

    “Multitask learning (Caruana, 1998) and task transfer have a rich history in machine learning (e.g., using ImageNet in the computer vision community (Huh et al., 2016)), as well as in NLP in particular (Collobert and Weston, 2008).”
    Method
  • Elasticsearch: The Definitive Guide

    Gormley, C., & Tong, Z. (2015) · Cited by 189

  • Modeling of the Question Answering Task in the YodaQA System

    Baudiš, P., & Šedivý, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24027-5_20 · Cited by 150

  • WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia

    Hewlett, D., Lacoste, A., Jones, L., Polosukhin, I., Fandrianto, A., Han, J., Kelcey, M., & Berthelot, D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1145 · Cited by 121 · cited 3×

    “That subfield has made considerable progress recently thanks to new deep learning architectures like attention-based and memory-1 augmented neural networks (Bahdanau et al., 2015; Weston et al., 2015; Graves et al., 2014) and release of new training and evaluation datasets like QuizBowl (Iyyer et al., 2014), CNN/Daily…”
    Background
  • Open Domain Question Answering via Semantic Enrichment

    Sun, H., Ma, H., Yih, W.-T., Tsai, C.-T., Liu, J., & Chang, M.-W. (2015) · International World Wide Web Conference (WWW) · doi:10.1145/2736277.2741651 · Cited by 114 · cited 3×

    “There are a number of highly developed full pipeline QA approaches using either the Web, as does QuASE (Sun et al., 2015), or Wikipedia as a resource, as do Microsoft’s AskMSR (Brill et al., 2002), IBM’s DeepQA (Ferrucci et al., 2010) and YodaQA (Baudi ˇ s, 2015; Baudi ˇ s and ˇSediv ` y, 2015) — the latter of which i…”
    Method
  • Learning Recurrent Span Representations for Extractive Question Answering

    Lee, K., Salant, S., Kwiatkowski, T., Parikh, A. P., Das, D., & Berant, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01436 · Cited by 108 · cited 3×

    “• Aligned question embedding : Following (Lee et al., 2016) and other recent works, the last part we incorporate is an aligned question embedding f align ( p i ) = j a i,j E ( q j ) , where the attention score a i,j captures the similarity between p i and each question words q j .”
    BackgroundInfluential
  • Multi-Perspective Context Matching for Machine Comprehension

    Wang, Z., Mi, H., Hamza, W., & Florian, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.04211 · Cited by 96

  • Using Wikipedia at the TREC QA Track

    Ahn, D., Jijkoun, V., Mishne, G., Müller, K., de Rijke, M., & Stefan Schlobach, A. (2005) · UvA-DARE (University of Amsterdam) · Cited by 91

  • Open domain question answering using Wikipedia-based knowledge model

    Ryu, P.-M., Jang, M.-G., & Kim, H. (2014) · Information Processing & Management · doi:10.1016/j.ipm.2014.04.007 · Cited by 68 · cited 2×

    “The authors of (Ryu et al., 2014) perform open-domain QA using a Wikipedia-based knowledge model.”
    Method
  • Mining Knowledge fromWikipedia for the Question Answering task

    Buscaldi, D., & Rosso, P. (2006) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2nvsc5puovct · Cited by 50 · cited 1×

    “Buscaldi and Rosso (2006) also mine knowledge from Wikipedia for QA.”
    Background

Research works printed but not linked: 5

  1. Petr Baudiˇ s. 2015. YodaQA: a modular question answering system pipeline. In POSTER 2015-19th International Student Conference on Electrical Engineering . pages 1156-1165.
  2. Eric Brill, Susan Dumais, and Michele Banko. 2002. Ananalysis of the AskMSR question-answering system. In Empirical Methods in Natural Language Processing (EMNLP) . pages 257-264.
  3. Rudolf Kadlec, Ondrej Bajgar, and Jan Kleindienst. 2016. From particular to general: A preliminary case study of transfer learning in reading comprehension. Machine Intelligence Workshop, NIPS .
  4. Alexander H. Miller, Adam Fisch, Jesse Dodge, AmirHossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. In Empirical Methods in Natural Language Processing (EMNLP) . pages 14001409.
  5. Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In International Conference on Learning Representations (ICLR) .

Cited by

  • Dense passage retrieval for open-domain question answering

    Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575

    Self-citation
  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

    Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101

    “As a demonstration, we build an index using the DrQA Wikipedia dump [5], (dated December 21st, 2016) and compare generations from RAG using this index to the newer index used in our main results (December 20th, 2018).”
    BackgroundMethodResult
  • Natural Questions: A benchmark for question answering research

    Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069

    “Short answer selection Given a long answer, the Document Reader model (Chen et al., 2017), abbreviated DocReader, is used to extract short answers.”
    Method
  • Language Models as Knowledge Bases?

    Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834

    “DrQA: Chen et al. (2017) introduce DrQA, a popular system for open-domain question answering.”
    Background
  • HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

    Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804

    “ample we employ bigram tf-idf (Chen et al., 2017) to retrieve 8 paragraphs from Wikipedia as distractors, using the question as the query.”
    Method

See all 1,546

Metadata

Authors
Chen, D., Fisch, A., Weston, J., & Bordes, A.
Affiliations
Meta (United States) (US)
Venue
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Published
2017
Pages
1870-1879
ISSN
0736-587X (ISSN-L)
OpenAlex
W2962985038
Cited by
1,546
References
39
Citations by year
2026: 61 · 2025: 105 · 2024: 123 · 2023: 218 · 2022: 209 · 2021: 268 · 2020: 202 · 2019: 199 · 2018: 142 · 2017: 18
FWCI
69.97
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
open-domain question answering, Wikipedia, machine reading, document retrieval, recurrent neural networks, multi-task learning, distant supervision, factoid questions

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.

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.