The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Complex Temporal Question Answering on Knowledge Graphs
Abstract
Question answering over knowledge graphs (KG-QA) is a vital topic in IR. Questions with temporal intent are a special class of practical importance, but have not received much attention in research. This work presents EXAQT, the first end-to-end system for answering complex temporal questions that have multiple entities and predicates, and associated temporal conditions. EXAQT answers natural language questions over KGs in two stages, one geared towards high recall, the other towards precision at top ranks. The first step computes question-relevant compact subgraphs within the KG, and judiciously enhances them with pertinent temporal facts, using Group Steiner Trees and fine-tuned BERT models. The second step constructs relational graph convolutional networks (R-GCNs) from the first step's output, and enhances the R-GCNs with time-aware entity embeddings and attention over temporal relations. We evaluate EXAQT on TimeQuestions, a large dataset of 16k temporal questions we compiled from a variety of general purpose KG-QA benchmarks. Results show that EXAQT outperforms three state-of-the-art systems for answering complex questions over KGs, thereby justifying specialized treatment of temporal QA.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
In the citing paper
“TimeQuestions is another challenging dataset, which has 16K temporal questions and is divided into four categories.However, TimeQuestions only includes a time granularity of years and is much smaller in size.”
From TimeR4 : Time-aware Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering (2024) · cites this paper as Jia et al., 2021
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Maintaining knowledge about temporal intervals
Allen, J. F. (1983) · Communications of the ACM · doi:10.1145/182.358434 · Cited by 7,593 · cited 3×
“Ans. when was james cagney’s spouse born? when was the last time the orioles won the world series?”
BackgroundFreebase: 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
Leveraging Linguistic Structure For Open Domain Information Extraction
Angeli, G., Johnson Premkumar, M. J., & Manning, C. D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1034 · Cited by 725
The Web as a Knowledge-Base for Answering Complex Questions
Talmor, A., & Berant, J. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1059 · Cited by 520 · cited 1×
“Free917 [19] 44 4 76 11 135 WebQ [13] 315 77 283 113 788 ComplexQ [11] 217 131 43 33 424 GraphQ [63] 264 30 13 42 349 ComplexWebQ [68] 1356 224 595 315 2490 ComQA [2] 669 355 1180 1587 3791 LC-QuAD [69] 122 19 0 26 167 LC-QuAD 2.”
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
Survey of Temporal Information Retrieval and Related Applications
Campos, R., Dias, G., Jorge, A. M., & Jatowt, A. (2015) · ACM Computing Surveys · doi:10.1145/2619088 · Cited by 262
Time-aware language models as temporal knowledge bases
Dhingra, B., Cole, J. R., Eisenschlos, J. M., Gillick, D., Eisenstein, J., & Cohen, W. W. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00459 · Cited by 212 · cited 1×
“Of late, understanding large KGs as a dynamic body of knowledge has gained attention, giving rise to the notion of temporal knowledge graphs or temporal knowledge bases [25, 70].”
BackgroundMessage Passing for Complex Question Answering over Knowledge Graphs
Vakulenko, S., Fernandez Garcia, J. D., Polleres, A., de Rijke, M., & Cochez, M. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3358026 · Cited by 14 · cited 16×
“Temporal questions have been underexplored in QA, and so has temporal information in KGs, despite their importance for knowledge workers like analysts or journalists as well as advanced information needs of lay users.”
BackgroundInfluential
Research works printed but not linked: 68
- 10.1145/3178876.3186004 · DOI
- Abdalghani Abujabal , Rishiraj Saha Roy , Mohamed Yahya, and Gerhard Weikum. 2019 . ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters. In NAACL-HLT. Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, and Gerhard Weikum. 2019. ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters. In NAACL-HLT.
- 10.1145/3038912.3052583 · DOI · Paper page
- 10.5555/1287369.1287473 · doi:10.5555/1287369.1287473
- David Ahn , Steven Schockaert , Martine De Cock, and Etienne Kerre . 2006 . Supporting temporal question answering: Strategies for offline data collection. In ICoS- 5. David Ahn, Steven Schockaert, Martine De Cock, and Etienne Kerre. 2006. Supporting temporal question answering: Strategies for offline data collection. In ICoS-5.
- 10.1145/1328964.1328968 · DOI · Paper page
- Omar Alonso , Jannik Strötgen , Ricardo Baeza-Yates , and Michael Gertz . 2011 . Temporal Information Retrieval: Challenges and Opportunities . TWAW , Vol. 11 (2011). Omar Alonso, Jannik Strötgen, Ricardo Baeza-Yates, and Michael Gertz. 2011. Temporal Information Retrieval: Challenges and Opportunities. TWAW, Vol. 11 (2011).
- 10.5555/1785162.1785216 · doi:10.5555/1785162.1785216
- Junwei Bao Nan Duan Zhao Yan Ming Zhou and Tiejun Zhao. 2016. Constraint-based question answering with knowledge graph. In COLING. Junwei Bao Nan Duan Zhao Yan Ming Zhou and Tiejun Zhao. 2016. Constraint-based question answering with knowledge graph. In COLING.
- 10.1145/2806416.2806472 · DOI · Paper page
- Jonathan Berant Andrew Chou Roy Frostig and Percy Liang. 2013. Semantic parsing on freebase from question-answer pairs. In EMNLP. Jonathan Berant Andrew Chou Roy Frostig and Percy Liang. 2013. Semantic parsing on freebase from question-answer pairs. In EMNLP.
- 10.1007/978-3-642-12275-0_5 · DOI · Paper page
- 10.1145/3357384.3357874 · DOI
- 10.1145/3357384.3358033 · DOI
- 10.1016/0004-3702(72)90040-9 · DOI
- Qingqing Cai and Alexander Yates. 2013. Large-scale semantic parsing via schema matching and lexicon extension. In ACL. Qingqing Cai and Alexander Yates. 2013. Large-scale semantic parsing via schema matching and lexicon extension. In ACL.
- 10.14778/3229863.3236252 · DOI
- Tarc'i sio Souza Costa Simon Gottschalk and Elena Demidova. 2020. Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs. In CIKM. Tarc'i sio Souza Costa Simon Gottschalk and Elena Demidova. 2020. Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs. In CIKM. · DOI
- 10.1145/3308558.3314124 · DOI
- Bolin Ding , Jeffrey Xu Yu , Shan Wang, Lu Qin, Xiao Zhang, and Xuemin Lin. 2007 . Finding top-k min-cost connected trees in databases. In ICDE. Bolin Ding, Jeffrey Xu Yu, Shan Wang, Lu Qin, Xiao Zhang, and Xuemin Lin. 2007. Finding top-k min-cost connected trees in databases. In ICDE.
- Mohnish Dubey Debayan Banerjee Abdelrahman Abdelkawi and Jens Lehmann. 2019. LC-QuAD 2.0: A large dataset for complex question answering over Wikidata and DBpedia. In ISWC. Mohnish Dubey Debayan Banerjee Abdelrahman Abdelkawi and Jens Lehmann. 2019. LC-QuAD 2.0: A large dataset for complex question answering over Wikidata and DBpedia. In ISWC. · DOI · Paper page
- 10.5555/2969442.2969488 · doi:10.5555/2969442.2969488
- 10.1145/1871437.1871689 · DOI · Paper page
- Alberto Garcia-Duran , Sebastijan Dumanvc ić, and Mathias Niepert . 2018 . Learning Sequence Encoders for Temporal Knowledge Graph Completion. In EMNLP. Alberto Garcia-Duran, Sebastijan Dumanvc ić, and Mathias Niepert. 2018. Learning Sequence Encoders for Temporal Knowledge Graph Completion. In EMNLP.
- Rishab Goel , Seyed Mehran Kazemi , Marcus Brubaker, and Pascal Poupart. 2020 . Diachronic embedding for temporal knowledge graph completion. In AAAI. Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker, and Pascal Poupart. 2020. Diachronic embedding for temporal knowledge graph completion. In AAAI.
- Sanda Harabagiu and Cosmin Adrian Bejan . 2005 . Question answering based on temporal inference . In AAAI Workshop on inference for textual question answering. Sanda Harabagiu and Cosmin Adrian Bejan. 2005. Question answering based on temporal inference. In AAAI Workshop on inference for textual question answering.
- 10.1109/TKDE.2003.1208999 · DOI · Paper page
- 10.5555/2145432.2145521 · doi:10.5555/2145432.2145521
- Zhen Jia , Abdalghani Abujabal , Rishiraj Saha Roy , Jannik Strötgen, and Gerhard Weikum. 2018 a. TempQuestions: A benchmark for temporal question answering. In HQA. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Strötgen, and Gerhard Weikum. 2018a. TempQuestions: A benchmark for temporal question answering. In HQA.
- 10.1145/3269206.3269247 · DOI · Paper page
- 10.1145/3404835.3462859 · DOI
- 10.1145/2911451.2914805 · DOI
- 10.1145/2872427.2883055 · DOI
- Timothée Lacroix Guillaume Obozinski and Nicolas Usunier. 2020. Tensor Decompositions for temporal knowledge base completion. In ICLR. Timothée Lacroix Guillaume Obozinski and Nicolas Usunier. 2020. Tensor Decompositions for temporal knowledge base completion. In ICLR.
- Julien Leblay and Melisachew Wudage Chekol. 2018. Deriving validity time in knowledge graph. In TempWeb. Julien Leblay and Melisachew Wudage Chekol. 2018. Deriving validity time in knowledge graph. In TempWeb. · DOI · Paper page
- Belinda Z. Li Sewon Min Srinivasan Iyer Yashar Mehdad and Wen-tau Yih. 2020. Efficient One-Pass End-to-End Entity Linking for Questions. In EMNLP. Belinda Z. Li Sewon Min Srinivasan Iyer Yashar Mehdad and Wen-tau Yih. 2020. Efficient One-Pass End-to-End Entity Linking for Questions. In EMNLP. · DOI
- 10.1145/2882903.2915217 · DOI
- 10.1002/int.20502 · DOI
- 10.1145/3331184.3331252 · DOI
- 10.5555/2999792.2999959 · doi:10.5555/2999792.2999959
- Borja Navarro-Colorado and Estela Saquete. 2015. Combining temporal information and topic modeling for cross-document event ordering. In arXiv. Borja Navarro-Colorado and Estela Saquete. 2015. Combining temporal information and topic modeling for cross-document event ordering. In arXiv. · doi:10.18653/v1/s15-2138
- Barlas Oguz Xilun Chen Vladimir Karpukhin Stan Peshterliev Dmytro Okhonko Michael Schlichtkrull Sonal Gupta Yashar Mehdad and Scott Yih. 2021. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering. In arXiv. Barlas Oguz Xilun Chen Vladimir Karpukhin Stan Peshterliev Dmytro Okhonko Michael Schlichtkrull Sonal Gupta Yashar Mehdad and Scott Yih. 2021. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering. In arXiv. · DOI · Paper page
- Jeffrey Pennington Richard Socher and Christopher Manning. 2014. GloVe: Global vectors for word representation. In EMNLP. Jeffrey Pennington Richard Socher and Christopher Manning. 2014. GloVe: Global vectors for word representation. In EMNLP. · DOI · Paper page
- Soumajit Pramanik , Jesujoba Alabi , Rishiraj Saha Roy, and Gerhard Weikum . 2021 . UNIQORN : Unified Question Answering over RDF Knowledge Graphs and Natural Language Text. In arXiv. Soumajit Pramanik, Jesujoba Alabi, Rishiraj Saha Roy, and Gerhard Weikum. 2021. UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text. In arXiv.
- James Pustejovsky , Janyce Wiebe , and Mark Maybury . 2002 . Multiple-perspective and temporal question answering . In Question Answering: Strategy and Resources Workshop Program. James Pustejovsky, Janyce Wiebe, and Mark Maybury. 2002. Multiple-perspective and temporal question answering. In Question Answering: Strategy and Resources Workshop Program.
- 10.1145/3336191.3371812 · DOI
- 10.1145/3397271.3401421 · DOI
- 10.5555/1641503.1641521 · doi:10.5555/1641503.1641521
- Apoorv Saxena Soumen Chakrabarti and Partha Talukdar. 2021. Question Answering Over Temporal Knowledge Graphs. In ACL. Apoorv Saxena Soumen Chakrabarti and Partha Talukdar. 2021. Question Answering Over Temporal Knowledge Graphs. In ACL. · DOI · Paper page
- Michael Schlichtkrull , Thomas N Kipf , Peter Bloem , Rianne Van Den Berg , Ivan Titov, and Max Welling. 2018 . Modeling relational data with graph convolutional networks. In ESWC. Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In ESWC.
- 10.1145/3366423.3380110 · doi:10.1145/3366423.3380110
- 10.5555/1859664.1859735 · doi:10.5555/1859664.1859735
- Yu Su Huan Sun Brian Sadler Mudhakar Srivatsa Izzeddin Gür Zenghui Yan and Xifeng Yan. 2016. On generating characteristic-rich question sets for QA evaluation. In EMNLP. Yu Su Huan Sun Brian Sadler Mudhakar Srivatsa Izzeddin Gür Zenghui Yan and Xifeng Yan. 2016. On generating characteristic-rich question sets for QA evaluation. In EMNLP. · DOI
- 10.1145/1242572.1242667 · DOI · Paper page
- Haitian Sun Tania Bedrax-Weiss and William Cohen. 2019. PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text. In EMNLP-IJCNLP. Haitian Sun Tania Bedrax-Weiss and William Cohen. 2019. PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text. In EMNLP-IJCNLP.
- Haitian Sun Bhuwan Dhingra Manzil Zaheer Kathryn Mazaitis Ruslan Salakhutdinov and William Cohen. 2018. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. In EMNLP. Haitian Sun Bhuwan Dhingra Manzil Zaheer Kathryn Mazaitis Ruslan Salakhutdinov and William Cohen. 2018. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. In EMNLP.
- 10.14778/3450980.3450982 · DOI
- Priyansh Trivedi Gaurav Maheshwari Mohnish Dubey and Jens Lehmann. 2017b. LC-QuAD: A corpus for complex question answering over knowledge graphs. In ISWC. Priyansh Trivedi Gaurav Maheshwari Mohnish Dubey and Jens Lehmann. 2017b. LC-QuAD: A corpus for complex question answering over knowledge graphs. In ISWC. · DOI · Paper page
- 10.5555/3305890.3306039 · doi:10.5555/3305890.3306039
- 10.1109/ICSC.2012.34 · DOI
- 10.1145/3397271.3401416 · doi:10.1145/3397271.3401416
- 10.5555/3295222.3295349 · doi:10.5555/3295222.3295349
- 10.1145/2629489 · DOI · Paper page
- 10.3390/fi12030045 · DOI
- 10.1145/2505515.2505677 · DOI
- Ikuya Yamada Akari Asai Jin Sakuma Hiroyuki Shindo Hideaki Takeda Yoshiyasu Takefuji and Yuji Matsumoto. 2020. Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia. In EMNLP. Ikuya Yamada Akari Asai Jin Sakuma Hiroyuki Shindo Hideaki Takeda Yoshiyasu Takefuji and Yuji Matsumoto. 2020. Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia. In EMNLP. · DOI · Paper page
- Wen-tau Yih Ming-Wei Chang Xiaodong He and Jianfeng Gao. 2015. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. In ACL-IJCNLP. Wen-tau Yih Ming-Wei Chang Xiaodong He and Jianfeng Gao. 2015. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. In ACL-IJCNLP.
- 10.1145/3336191.3371847 · DOI
Cited by
Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning
Fatemi, B., Kazemi, M., Tsitsulin, A., Malkan, K., Yim, J., Palowitch, J., Seo, S., Halcrow, J., & Perozzi, B. (2024) · arXiv · doi:10.48550/arxiv.2406.09170 · Cited by 101
Qian, X., Zhang, Y., Zhao, Y., Zhou, B., Sui, X., Zhang, L., & Song, K. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.394 · Cited by 35
“As for TimeQuestions, TimeR 4 also achieves the best results across all question types.”
MethodInfluentialStreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
Liška, A., Kočiský, T., Gribovskaya, E., Terzi, T., Sezener, E., Agrawal, D., d'Autume, C. D. M., Scholtes, T., Zaheer, M., Young, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11388 · Cited by 19
TempoQR: Temporal Question Reasoning over Knowledge Graphs
Mavromatis, C., Subramanyam, P. L., Ioannidis, V. N., Adeshina, A., Howard, P. R., Grinberg, T., Hakim, N., & Karypis, G. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20526 · Cited by 16
MRAG: a modular retrieval framework for time-sensitive question answering
Zhang, S., Xue, Y., Zhang, Y., Wu, X., Luu, A. T., & Zhao, C. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.167 · Cited by 3
Metadata
- Authors
- Jia, Z., Pramanik, S., Saha Roy, R., & Weikum, G.
- Affiliations
- Southwest Jiaotong University, Chengdu, China
- Indian Institute of Technology Bhilai, Bhilai, India
- Max Planck Institute for Informatics, Saarbruecken, Germany
- Venue
- Proceedings of the 30th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2021-10-26
- Pages
- 792-802
- Cited by
- 74
- References
- 9
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.