It's High Time: A Survey of Temporal Question Answering

Abdelrahman Abdallah; Adam Jatowt; Avishek Anand; Bhawna Piryani; Jamshid Mozafari

arxiv: 2505.20243 · v4 · submitted 2025-05-26 · 💻 cs.CL · cs.IR

It's High Time: A Survey of Temporal Question Answering

Bhawna Piryani , Abdelrahman Abdallah , Jamshid Mozafari , Avishek Anand , Adam Jatowt This is my paper

Pith reviewed 2026-05-19 12:59 UTC · model grok-4.3

classification 💻 cs.CL cs.IR

keywords temporal question answeringsurveytemporal reasoningcorpus temporalityquestion temporalitymodel capabilitiesdatasetsbenchmarks

0 comments

The pith

A tripartite taxonomy of corpus temporality, question temporality, and model capabilities unifies the temporal question answering literature.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The survey reviews temporal question answering, a task that requires systems to handle questions with explicit or implicit time constraints drawn from time-stamped sources such as news archives and knowledge bases. It proposes organizing the field around the interactions among three elements: how time appears in the underlying corpus, how time is expressed in the question, and what temporal capabilities a model possesses. This structure supports side-by-side comparison of datasets, tasks, and methods. The review also covers advances enabled by transformer architectures and large language models, including temporal language modeling, retrieval-augmented generation, and evaluation benchmarks that test robustness to time-related phenomena.

Core claim

The paper establishes a unified perspective that captures the interaction between corpus temporality, question temporality, and model capabilities, enabling a systematic comparison of datasets, tasks, and approaches across the temporal question answering literature.

What carries the argument

The tripartite taxonomy consisting of corpus temporality, question temporality, and model capabilities, which serves as the organizing lens for comparing existing work.

If this is right

Datasets and approaches can be compared systematically along the three temporality dimensions.
Progress in transformer-based and LLM methods for temporal reasoning can be situated relative to specific combinations of corpus, question, and model temporality.
Challenges such as temporal intent detection, time normalization, event ordering, and reasoning over evolving facts receive a shared analytical structure.
Benchmark design and evaluation strategies can be assessed for how well they probe each temporality type.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The taxonomy may help identify gaps where new datasets should target underrepresented combinations of the three temporality types.
Model development could prioritize testing performance when corpus temporality and question temporality are deliberately mismatched.
The same lens might be applied to related time-sensitive tasks such as temporal summarization or event timeline construction.

Load-bearing premise

The tripartite taxonomy is comprehensive and non-overlapping enough to classify the entire body of temporal question answering research without significant omissions or forced fits.

What would settle it

A new temporal question answering paper or method that cannot be placed within the categories of corpus temporality, question temporality, or model capabilities would challenge the taxonomy's claimed coverage.

Figures

Figures reproduced from arXiv: 2505.20243 by Abdelrahman Abdallah, Adam Jatowt, Avishek Anand, Bhawna Piryani, Jamshid Mozafari.

**Figure 2.** Figure 2: Taxonomy of Temporal Datasets and Evaluation benchmarks, Tasks, and Approaches. [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗

read the original abstract

Time plays a critical role in how information is generated, retrieved, and interpreted. In this survey, we provide a comprehensive overview of Temporal Question Answering (TQA), a research area that focuses on answering questions involving temporal constraints or context. As time-stamped content from sources like news articles, web archives, and knowledge bases continues to grow, TQA systems must address challenges such as detecting temporal intent, normalizing time expressions, ordering events, and reasoning over evolving or ambiguous facts. We organize existing work through a unified perspective that captures the interaction between corpus temporality, question temporality, and model capabilities, enabling a systematic comparison of datasets, tasks, and approaches. We review recent advances in TQA enabled by neural architectures, especially transformer-based models and Large Language Models (LLMs), highlighting progress in temporal language modeling, retrieval-augmented generation (RAG), and temporal reasoning. We also discuss benchmark datasets and evaluation strategies designed to test temporal robustness,

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This survey frames TQA around corpus-question-model temporality interactions to organize datasets and methods, which is a practical but incremental step.

read the letter

Colleague, the main thing to know is that this survey tries to organize temporal question answering by looking at how corpus temporality, question temporality, and model capabilities interact. That lens lets them line up existing work more systematically than a simple list of papers or tasks. It is the clearest new element here. The paper does a decent job pulling together the standard topics like time normalization, event ordering, and how transformers and LLMs handle temporal reasoning. It also covers retrieval-augmented approaches and the main benchmarks, which gives a reader a reasonable map of where the field stands right now. The review of evaluation strategies is straightforward and points out some robustness issues. The soft spot is the taxonomy itself. The three categories overlap in practice, and some temporal reasoning tasks sit across all of them, so the framework may require more qualification than the abstract suggests. As a survey it adds no new experiments or data, which is expected but keeps the contribution at the level of organization rather than discovery. Coverage looks broad from the structure, though very recent LLM-specific papers could still be thin. This is for NLP and IR researchers who need a quick way to compare TQA datasets or spot gaps before starting new work. A reader who wants an entry point or a way to frame their own experiments would find it useful. It deserves a serious referee because the organizing idea is clear enough to influence how others present their results, even if the taxonomy needs tightening in review.

Referee Report

0 major / 3 minor

Summary. The paper surveys Temporal Question Answering (TQA), a subfield addressing questions with temporal constraints or context from time-stamped sources such as news and knowledge bases. It organizes the literature via a tripartite taxonomy of corpus temporality, question temporality, and model capabilities to enable systematic comparison of datasets, tasks, and approaches. The survey reviews neural and LLM-based advances in temporal language modeling, retrieval-augmented generation, and temporal reasoning, along with benchmarks and evaluation strategies for temporal robustness.

Significance. If the taxonomy proves comprehensive and non-overlapping, the survey would meaningfully structure a growing research area, facilitating comparisons across TQA work and highlighting gaps in temporal robustness for transformers and LLMs. As a literature survey, its value lies in coverage and organization rather than novel derivations; the absence of post-hoc exclusions or self-referential claims supports its utility for researchers entering or advancing the field.

minor comments (3)

[Abstract] The abstract ends abruptly at 'temporal robustness,'; complete the sentence to ensure the overview of evaluation strategies is fully stated.
[§3] §3 (Taxonomy section): provide explicit decision criteria or boundary examples showing how the three categories remain non-overlapping when a single paper addresses both corpus and question temporality simultaneously.
[Dataset comparison table] Table 1 or equivalent dataset overview: include publication years for all cited datasets to allow readers to assess recency of coverage.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive evaluation of our survey on Temporal Question Answering. We appreciate the recommendation for minor revision and note that no specific major comments were raised in the report. We will incorporate any minor suggestions during the revision process to further improve clarity and coverage.

Circularity Check

0 steps flagged

No significant circularity: standard survey organization

full rationale

This is a literature survey paper whose central contribution is a proposed tripartite taxonomy (corpus temporality, question temporality, model capabilities) for organizing existing TQA work. No derivations, equations, predictions, or fitted parameters appear in the provided abstract or described structure. The taxonomy is presented as an organizing device rather than a self-defined or self-cited result that reduces to its own inputs. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked in a manner that creates circularity. The paper summarizes external literature without reducing any result to quantities defined by its own constructs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

As a survey the paper rests on the existence and representativeness of the prior TQA literature plus standard assumptions in NLP about temporal expressions being normalizable and events being orderable. No free parameters or invented entities are introduced.

axioms (1)

domain assumption Temporal expressions in text can be normalized to a standard form and events can be ordered along a timeline.
Invoked when discussing detection of temporal intent and ordering events as core TQA challenges.

pith-pipeline@v0.9.0 · 5710 in / 1233 out tokens · 33061 ms · 2026-05-19T12:59:13.117518+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We organize existing work through a unified perspective that captures the interaction between corpus temporality, question temporality, and model capabilities
IndisputableMonolith/Foundation/ArrowOfTime.lean arrow_from_z unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

temporal reasoning, event ordering, timeline construction

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

32 extracted references · 32 canonical work pages · 1 internal anchor

[1]

Omar Alonso, Michael Gertz, and Ricardo Baeza-Yates

On the value of temporal information in infor- mation retrieval.SIGIR Forum, 41(2):35–41. Omar Alonso, Michael Gertz, and Ricardo Baeza-Yates

work page
[2]

InProceedings of the 18th ACM Conference on Information and Knowl- edge Management, CIKM ’09, page 97–106, New York, NY , USA

Clustering and exploring search results us- ing timeline constructions. InProceedings of the 18th ACM Conference on Information and Knowl- edge Management, CIKM ’09, page 97–106, New York, NY , USA. Association for Computing Machin- ery. Omar Alonso, Jannik Strötgen, Ricardo Baeza-Yates, and Michael Gertz. 2011. Temporal information re- trieval: Challenge...

work page 2011
[3]

InSecond ACM International Conference on Web Search and Data Mining

Time will tell: Leveraging temporal expres- sions in ir. InSecond ACM International Conference on Web Search and Data Mining. ACM. Anab Maulana Barik, Wynne Hsu, and Mong-Li Lee

work page
[4]

InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing: Industry Track, pages 657–664, Miami, Florida, US

Time matters: An end-to-end solution for tem- poral claim verification. InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing: Industry Track, pages 657–664, Miami, Florida, US. Association for Computational Linguistics. Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, and Adrià de Gispert. 2025. Learning to reason over ti...

work page 2024
[5]

InHumanities, computers and cultural heritage: Proceedings of the XVIth Interna- tional Conference of the Association for History and Computing (AHC 2005), pages 161–168

Temporal language models for the disclosure of historical text. InHumanities, computers and cultural heritage: Proceedings of the XVIth Interna- tional Conference of the Association for History and Computing (AHC 2005), pages 161–168. Koninklijke Nederlandse Academie van Wetenschappen. Irwin Deng, Kushagra Dixit, Dan Roth, and Vivek Gupta. 2025. Enhancing...

work page 2005
[6]

InFindings of the Association for Computational Linguistics: ACL 2025, pages 18974–18988, Vienna, Austria

TReMu: Towards neuro-symbolic temporal reasoning for LLM-agents with memory in multi- session dialogues. InFindings of the Association for Computational Linguistics: ACL 2025, pages 18974–18988, Vienna, Austria. Association for Com- putational Linguistics. Raphael Gruber, Abdelrahman Abdallah, Michael Fär- ber, and Adam Jatowt. 2025. ComplexTempQA: A 100m...

work page 2025
[7]

Archive TimeLine summarization (ATLS): Conceptual framework for timeline generation over historical document collections. InProceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 13–23, Gyeongju, Republic of Korea. International Conference on Com- putational Lingui...

work page
[8]

InProceedings of the 54th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 1489–1501, Berlin, Germany

Diachronic word embeddings reveal statisti- cal laws of semantic change. InProceedings of the 54th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 1489–1501, Berlin, Germany. Association for Com- putational Linguistics. Rujun Han, Xiang Ren, and Nanyun Peng. 2021. ECONET: Effective continual pretraining of ...

work page 2021
[9]

InPro- ceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing, pages 6750– 6774, Singapore

Do language models have a common sense regarding time? revisiting temporal commonsense reasoning in the era of large language models. InPro- ceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing, pages 6750– 6774, Singapore. Association for Computational Lin- guistics. Adam Jatowt, Ching-Man Au Yeung, and Katsumi Tanaka. 20...

work page 2023
[10]

In Web Information Systems Engineering–WISE 2005: 6th International Conference on Web Information Systems Engineering, New York, NY, USA, November 20-22, 2005

Temporal ranking of search engine results. In Web Information Systems Engineering–WISE 2005: 6th International Conference on Web Information Systems Engineering, New York, NY, USA, November 20-22, 2005. Proceedings 6, pages 43–52. Springer. Adam Jatowt, Yukiko Kawai, and Katsumi Tanaka

work page 2005
[11]

InProceedings of the 9th Annual ACM International Workshop on Web Information and Data Management, WIDM ’07, page 137–144, New York, NY , USA

Detecting age of page content. InProceedings of the 9th Annual ACM International Workshop on Web Information and Data Management, WIDM ’07, page 137–144, New York, NY , USA. Association for Computing Machinery. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jan- nik Strötgen, and Gerhard Weikum. 2018. Tempques- tions: A benchmark for temporal question ...

work page 2018
[12]

InCompan- ion Proceedings of the ACM Web Conference 2024, WWW ’24, page 1394–1399, New York, NY , USA

Tiq: A benchmark for temporal question an- swering with implicit time constraints. InCompan- ion Proceedings of the ACM Web Conference 2024, WWW ’24, page 1394–1399, New York, NY , USA. Association for Computing Machinery. Zhen Jia, Soumajit Pramanik, Rishiraj Saha Roy, and Gerhard Weikum. 2021. Complex temporal question answering on knowledge graphs. InP...

work page 2024
[13]

ForecastQA: A question answering challenge for event forecasting with temporal text data. In Proceedings of the 59th Annual Meeting of the Asso- ciation for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4636– 4650, Online. Association for Computational Lin- guistics. Hid...

work page 2013
[14]

InProceedings of the 35th International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, SIGIR ’12, page 1099–1100, New York, NY , USA

Learning to select a time-aware retrieval model. InProceedings of the 35th International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, SIGIR ’12, page 1099–1100, New York, NY , USA. Association for Computing Machin- ery. Nattiya Kanhabua, Roi Blanco, and Kjetil Nørvåg. 2015. Temporal information retrieval.Found. Trends Inf. ...

work page 2015
[15]

Curran Associates, Inc

Realtime qa: What's the answer right now? In Advances in Neural Information Processing Systems, volume 36, pages 49025–49043. Curran Associates, Inc. Phi Manh Kien, Ha-Thanh Nguyen, Ngo Xuan Bach, Vu Tran, Minh Le Nguyen, and Tu Minh Phuong

work page
[16]

InProceedings of the 28th International Conference on Computational Lin- guistics, pages 988–998, Barcelona, Spain (Online)

Answering legal questions by learning neural attentive text representation. InProceedings of the 28th International Conference on Computational Lin- guistics, pages 988–998, Barcelona, Spain (Online). International Committee on Computational Linguis- tics. Mei Kobayashi and Koichi Takeda. 2000. Informa- tion retrieval on the web.ACM Comput. Surv., 32(2):1...

work page 2000
[17]

Dating Texts without Explicit Temporal Cues

A survey on question answering technology from an information retrieval perspective.Informa- tion Sciences, 181(24):5412–5434. Anagha Kulkarni, Jaime Teevan, Krysta M. Svore, and Susan T. Dumais. 2011. Understanding temporal query dynamics. InProceedings of the Fourth ACM International Conference on Web Search and Data Mining, WSDM ’11, page 167–176, New ...

work page internal anchor Pith review Pith/arXiv arXiv 2011
[18]

Conditional generation of temporally-ordered event sequences. InProceedings of the 59th Annual Meeting of the Association for Computational Lin- guistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7142–7157, Online. Association for Computational Linguistics. Adam Liska, Tomas Kocisky, Elena Gr...

work page 2022
[19]

TIMERS: Document-level temporal relation extraction. InProceedings of the 59th Annual Meet- ing of the Association for Computational Linguistics and the 11th International Joint Conference on Natu- ral Language Processing (Volume 2: Short Papers), pages 524–533, Online. Association for Computa- tional Linguistics. Vaibhav Mavi, Anubhav Jangra, Adam Jatowt, et al

work page
[20]

Pawel Mazur and Robert Dale

Multi-hop question answering.Foundations and Trends® in Information Retrieval, 17(5):457– 586. Pawel Mazur and Robert Dale. 2010. WikiWars: A new corpus for research on temporal expressions. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 913– 922, Cambridge, MA. Association for Computational Linguistics. J...

work page arXiv 2010
[21]

InProceedings of the 20th Annual SIGdial Meeting on Discourse and Dia- logue, pages 239–249, Stockholm, Sweden

TDDiscourse: A dataset for discourse-level temporal ordering of events. InProceedings of the 20th Annual SIGdial Meeting on Discourse and Dia- logue, pages 239–249, Stockholm, Sweden. Associa- tion for Computational Linguistics. Vlad Niculae, Marcos Zampieri, Liviu Dinu, and Alina Maria Ciobanu. 2014. Temporal text rank- ing and automatic dating of texts....

work page 2014
[22]

Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and Adam Jatowt

Tkgqa dataset: Using question answering to guide and validate the evolution of temporal knowl- edge graph.Data, 8(3). Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and Adam Jatowt. 2024a. Detecting tem- poral ambiguity in questions. InFindings of the Asso- ciation for Computational Linguistics: EMNLP 2024, pages 9620–9634, Miami, Florida, USA. A...

work page arXiv 2024
[23]

InCorpus linguistics, volume 2003, page 40

The timebank corpus. InCorpus linguistics, volume 2003, page 40. Lancaster, UK. Xinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou, Xuhui Sui, Li Zhang, and Kehui Song. 2024. TimeR4 : Time-aware retrieval-augmented large language models for temporal knowledge graph question an- swering. InProceedings of the 2024 Conference on Empirical Methods in Natural Lan...

work page 2003
[24]

Estela Saquete, Jose L

Springer. Estela Saquete, Jose L. Vicedo, Patricio Martínez-Barco, Rafael Muñoz, and Hector Llorens. 2009. Enhancing qa systems with complex temporal question process- ing capabilities.Journal of Artificial Intelligence Research, 35(1):755–811. Apoorv Saxena, Soumen Chakrabarti, and Partha Taluk- dar. 2021. Question answering over temporal knowl- edge gra...

work page 2009
[25]

InProceedings of the 2016 ACM on conference on human information interaction and retrieval, pages 183–192

History by diversity: Helping historians search news archives. InProceedings of the 2016 ACM on conference on human information interaction and retrieval, pages 183–192. Daivik Sojitra, Raghav Jain, Sriparna Saha, Adam Ja- towt, and Manish Gupta. 2024. Timeline summariza- tion in the era of llms. InProceedings of the 47th International ACM SIGIR Conferenc...

work page arXiv 2016
[26]

InPro- ceedings of the 9th international semantic web con- ference on The semantic web-Volume Part II, pages 241–256

Time-oriented question answering from clini- cal narratives sing semantic-web techniques. InPro- ceedings of the 9th international semantic web con- ference on The semantic web-Volume Part II, pages 241–256. Adam Trischler, Tong Wang, Xingdi Yuan, Justin Har- ris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2017. NewsQA: A machine comprehen- s...

work page 2017
[27]

InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1615, Melbourne, Australia

Dating documents using graph convolution networks. InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1615, Melbourne, Australia. Association for Computational Linguistics. Siddharth Vashishtha, Benjamin Van Durme, and Aaron Steven White. 2019. Fine-grained temporal relation extrac...

work page 2019
[28]

InProceedings of the 45th Inter- national ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’22, page 3025–3035, New York, NY , USA

Archivalqa: A large-scale benchmark dataset for open-domain question answering over historical news collections. InProceedings of the 45th Inter- national ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’22, page 3025–3035, New York, NY , USA. Association for Computing Machinery. Jiexin Wang, Adam Jatowt, Masatoshi Yoshika...

work page arXiv 2023
[29]

InProceedings of the 33rd ACM International Conference on Informa- tion and Knowledge Management, CIKM ’24, page 2544–2553, New York, NY , USA

Time-sensitve retrieval-augmented genera- tion for question answering. InProceedings of the 33rd ACM International Conference on Informa- tion and Knowledge Management, CIKM ’24, page 2544–2553, New York, NY , USA. Association for Computing Machinery. Jiaying Wu and Bryan Hooi. 2025. Chain-of-timeline: Enhancing LLM zero-shot temporal reasoning with SQL-s...

work page 2025
[30]

Olympics 2024

Enhancing temporal sensitivity and reason- ing for time-sensitive question answering. InFind- ings of the Association for Computational Linguistics: EMNLP 2024, pages 14495–14508, Miami, Florida, USA. Association for Computational Linguistics. Zonglin Yang, Xinya Du, Alexander Rush, and Claire Cardie. 2020. Improving event duration prediction via time-awa...

work page arXiv 2024
[31]

Which case law was applica- ble prior to the 2015 amendment of the privacy statute?

were introduced. Other strategies focused on enhancing recency- aware retrieval. Jatowt et al. (2005) proposed re- ranking methods using archived web snapshots to favor fresher content, while Dong et al. (2010) in- corporated real-time Twitter signals, and Setty et al. (2017) used news signals into crawling and rank- ing to support time-sensitive queries....

work page 2005
[32]

What caused the economic crisis dur- ing Trump’s presidency?

and TOMATO (Shangguan et al., 2025) high- light the need for culturally and visually grounded temporal reasoning. Future research should fo- cus on developing multilingual temporal taggers, temporally annotated datasets in low-resource lan- guages, and cross-modal alignment techniques that jointly reason over text, images, and video to cap- ture time-rela...

work page 2025

[1] [1]

Omar Alonso, Michael Gertz, and Ricardo Baeza-Yates

On the value of temporal information in infor- mation retrieval.SIGIR Forum, 41(2):35–41. Omar Alonso, Michael Gertz, and Ricardo Baeza-Yates

work page

[2] [2]

InProceedings of the 18th ACM Conference on Information and Knowl- edge Management, CIKM ’09, page 97–106, New York, NY , USA

Clustering and exploring search results us- ing timeline constructions. InProceedings of the 18th ACM Conference on Information and Knowl- edge Management, CIKM ’09, page 97–106, New York, NY , USA. Association for Computing Machin- ery. Omar Alonso, Jannik Strötgen, Ricardo Baeza-Yates, and Michael Gertz. 2011. Temporal information re- trieval: Challenge...

work page 2011

[3] [3]

InSecond ACM International Conference on Web Search and Data Mining

Time will tell: Leveraging temporal expres- sions in ir. InSecond ACM International Conference on Web Search and Data Mining. ACM. Anab Maulana Barik, Wynne Hsu, and Mong-Li Lee

work page

[4] [4]

InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing: Industry Track, pages 657–664, Miami, Florida, US

Time matters: An end-to-end solution for tem- poral claim verification. InProceedings of the 2024 Conference on Empirical Methods in Natural Lan- guage Processing: Industry Track, pages 657–664, Miami, Florida, US. Association for Computational Linguistics. Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, and Adrià de Gispert. 2025. Learning to reason over ti...

work page 2024

[5] [5]

InHumanities, computers and cultural heritage: Proceedings of the XVIth Interna- tional Conference of the Association for History and Computing (AHC 2005), pages 161–168

Temporal language models for the disclosure of historical text. InHumanities, computers and cultural heritage: Proceedings of the XVIth Interna- tional Conference of the Association for History and Computing (AHC 2005), pages 161–168. Koninklijke Nederlandse Academie van Wetenschappen. Irwin Deng, Kushagra Dixit, Dan Roth, and Vivek Gupta. 2025. Enhancing...

work page 2005

[6] [6]

InFindings of the Association for Computational Linguistics: ACL 2025, pages 18974–18988, Vienna, Austria

TReMu: Towards neuro-symbolic temporal reasoning for LLM-agents with memory in multi- session dialogues. InFindings of the Association for Computational Linguistics: ACL 2025, pages 18974–18988, Vienna, Austria. Association for Com- putational Linguistics. Raphael Gruber, Abdelrahman Abdallah, Michael Fär- ber, and Adam Jatowt. 2025. ComplexTempQA: A 100m...

work page 2025

[7] [7]

Archive TimeLine summarization (ATLS): Conceptual framework for timeline generation over historical document collections. InProceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 13–23, Gyeongju, Republic of Korea. International Conference on Com- putational Lingui...

work page

[8] [8]

InProceedings of the 54th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 1489–1501, Berlin, Germany

Diachronic word embeddings reveal statisti- cal laws of semantic change. InProceedings of the 54th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 1489–1501, Berlin, Germany. Association for Com- putational Linguistics. Rujun Han, Xiang Ren, and Nanyun Peng. 2021. ECONET: Effective continual pretraining of ...

work page 2021

[9] [9]

InPro- ceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing, pages 6750– 6774, Singapore

Do language models have a common sense regarding time? revisiting temporal commonsense reasoning in the era of large language models. InPro- ceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing, pages 6750– 6774, Singapore. Association for Computational Lin- guistics. Adam Jatowt, Ching-Man Au Yeung, and Katsumi Tanaka. 20...

work page 2023

[10] [10]

In Web Information Systems Engineering–WISE 2005: 6th International Conference on Web Information Systems Engineering, New York, NY, USA, November 20-22, 2005

Temporal ranking of search engine results. In Web Information Systems Engineering–WISE 2005: 6th International Conference on Web Information Systems Engineering, New York, NY, USA, November 20-22, 2005. Proceedings 6, pages 43–52. Springer. Adam Jatowt, Yukiko Kawai, and Katsumi Tanaka

work page 2005

[11] [11]

InProceedings of the 9th Annual ACM International Workshop on Web Information and Data Management, WIDM ’07, page 137–144, New York, NY , USA

Detecting age of page content. InProceedings of the 9th Annual ACM International Workshop on Web Information and Data Management, WIDM ’07, page 137–144, New York, NY , USA. Association for Computing Machinery. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jan- nik Strötgen, and Gerhard Weikum. 2018. Tempques- tions: A benchmark for temporal question ...

work page 2018

[12] [12]

InCompan- ion Proceedings of the ACM Web Conference 2024, WWW ’24, page 1394–1399, New York, NY , USA

Tiq: A benchmark for temporal question an- swering with implicit time constraints. InCompan- ion Proceedings of the ACM Web Conference 2024, WWW ’24, page 1394–1399, New York, NY , USA. Association for Computing Machinery. Zhen Jia, Soumajit Pramanik, Rishiraj Saha Roy, and Gerhard Weikum. 2021. Complex temporal question answering on knowledge graphs. InP...

work page 2024

[13] [13]

ForecastQA: A question answering challenge for event forecasting with temporal text data. In Proceedings of the 59th Annual Meeting of the Asso- ciation for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4636– 4650, Online. Association for Computational Lin- guistics. Hid...

work page 2013

[14] [14]

InProceedings of the 35th International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, SIGIR ’12, page 1099–1100, New York, NY , USA

Learning to select a time-aware retrieval model. InProceedings of the 35th International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, SIGIR ’12, page 1099–1100, New York, NY , USA. Association for Computing Machin- ery. Nattiya Kanhabua, Roi Blanco, and Kjetil Nørvåg. 2015. Temporal information retrieval.Found. Trends Inf. ...

work page 2015

[15] [15]

Curran Associates, Inc

Realtime qa: What's the answer right now? In Advances in Neural Information Processing Systems, volume 36, pages 49025–49043. Curran Associates, Inc. Phi Manh Kien, Ha-Thanh Nguyen, Ngo Xuan Bach, Vu Tran, Minh Le Nguyen, and Tu Minh Phuong

work page

[16] [16]

InProceedings of the 28th International Conference on Computational Lin- guistics, pages 988–998, Barcelona, Spain (Online)

Answering legal questions by learning neural attentive text representation. InProceedings of the 28th International Conference on Computational Lin- guistics, pages 988–998, Barcelona, Spain (Online). International Committee on Computational Linguis- tics. Mei Kobayashi and Koichi Takeda. 2000. Informa- tion retrieval on the web.ACM Comput. Surv., 32(2):1...

work page 2000

[17] [17]

Dating Texts without Explicit Temporal Cues

A survey on question answering technology from an information retrieval perspective.Informa- tion Sciences, 181(24):5412–5434. Anagha Kulkarni, Jaime Teevan, Krysta M. Svore, and Susan T. Dumais. 2011. Understanding temporal query dynamics. InProceedings of the Fourth ACM International Conference on Web Search and Data Mining, WSDM ’11, page 167–176, New ...

work page internal anchor Pith review Pith/arXiv arXiv 2011

[18] [18]

Conditional generation of temporally-ordered event sequences. InProceedings of the 59th Annual Meeting of the Association for Computational Lin- guistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7142–7157, Online. Association for Computational Linguistics. Adam Liska, Tomas Kocisky, Elena Gr...

work page 2022

[19] [19]

TIMERS: Document-level temporal relation extraction. InProceedings of the 59th Annual Meet- ing of the Association for Computational Linguistics and the 11th International Joint Conference on Natu- ral Language Processing (Volume 2: Short Papers), pages 524–533, Online. Association for Computa- tional Linguistics. Vaibhav Mavi, Anubhav Jangra, Adam Jatowt, et al

work page

[20] [20]

Pawel Mazur and Robert Dale

Multi-hop question answering.Foundations and Trends® in Information Retrieval, 17(5):457– 586. Pawel Mazur and Robert Dale. 2010. WikiWars: A new corpus for research on temporal expressions. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 913– 922, Cambridge, MA. Association for Computational Linguistics. J...

work page arXiv 2010

[21] [21]

InProceedings of the 20th Annual SIGdial Meeting on Discourse and Dia- logue, pages 239–249, Stockholm, Sweden

TDDiscourse: A dataset for discourse-level temporal ordering of events. InProceedings of the 20th Annual SIGdial Meeting on Discourse and Dia- logue, pages 239–249, Stockholm, Sweden. Associa- tion for Computational Linguistics. Vlad Niculae, Marcos Zampieri, Liviu Dinu, and Alina Maria Ciobanu. 2014. Temporal text rank- ing and automatic dating of texts....

work page 2014

[22] [22]

Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and Adam Jatowt

Tkgqa dataset: Using question answering to guide and validate the evolution of temporal knowl- edge graph.Data, 8(3). Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, and Adam Jatowt. 2024a. Detecting tem- poral ambiguity in questions. InFindings of the Asso- ciation for Computational Linguistics: EMNLP 2024, pages 9620–9634, Miami, Florida, USA. A...

work page arXiv 2024

[23] [23]

InCorpus linguistics, volume 2003, page 40

The timebank corpus. InCorpus linguistics, volume 2003, page 40. Lancaster, UK. Xinying Qian, Ying Zhang, Yu Zhao, Baohang Zhou, Xuhui Sui, Li Zhang, and Kehui Song. 2024. TimeR4 : Time-aware retrieval-augmented large language models for temporal knowledge graph question an- swering. InProceedings of the 2024 Conference on Empirical Methods in Natural Lan...

work page 2003

[24] [24]

Estela Saquete, Jose L

Springer. Estela Saquete, Jose L. Vicedo, Patricio Martínez-Barco, Rafael Muñoz, and Hector Llorens. 2009. Enhancing qa systems with complex temporal question process- ing capabilities.Journal of Artificial Intelligence Research, 35(1):755–811. Apoorv Saxena, Soumen Chakrabarti, and Partha Taluk- dar. 2021. Question answering over temporal knowl- edge gra...

work page 2009

[25] [25]

InProceedings of the 2016 ACM on conference on human information interaction and retrieval, pages 183–192

History by diversity: Helping historians search news archives. InProceedings of the 2016 ACM on conference on human information interaction and retrieval, pages 183–192. Daivik Sojitra, Raghav Jain, Sriparna Saha, Adam Ja- towt, and Manish Gupta. 2024. Timeline summariza- tion in the era of llms. InProceedings of the 47th International ACM SIGIR Conferenc...

work page arXiv 2016

[26] [26]

InPro- ceedings of the 9th international semantic web con- ference on The semantic web-Volume Part II, pages 241–256

Time-oriented question answering from clini- cal narratives sing semantic-web techniques. InPro- ceedings of the 9th international semantic web con- ference on The semantic web-Volume Part II, pages 241–256. Adam Trischler, Tong Wang, Xingdi Yuan, Justin Har- ris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2017. NewsQA: A machine comprehen- s...

work page 2017

[27] [27]

InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1615, Melbourne, Australia

Dating documents using graph convolution networks. InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1615, Melbourne, Australia. Association for Computational Linguistics. Siddharth Vashishtha, Benjamin Van Durme, and Aaron Steven White. 2019. Fine-grained temporal relation extrac...

work page 2019

[28] [28]

InProceedings of the 45th Inter- national ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’22, page 3025–3035, New York, NY , USA

Archivalqa: A large-scale benchmark dataset for open-domain question answering over historical news collections. InProceedings of the 45th Inter- national ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’22, page 3025–3035, New York, NY , USA. Association for Computing Machinery. Jiexin Wang, Adam Jatowt, Masatoshi Yoshika...

work page arXiv 2023

[29] [29]

InProceedings of the 33rd ACM International Conference on Informa- tion and Knowledge Management, CIKM ’24, page 2544–2553, New York, NY , USA

Time-sensitve retrieval-augmented genera- tion for question answering. InProceedings of the 33rd ACM International Conference on Informa- tion and Knowledge Management, CIKM ’24, page 2544–2553, New York, NY , USA. Association for Computing Machinery. Jiaying Wu and Bryan Hooi. 2025. Chain-of-timeline: Enhancing LLM zero-shot temporal reasoning with SQL-s...

work page 2025

[30] [30]

Olympics 2024

Enhancing temporal sensitivity and reason- ing for time-sensitive question answering. InFind- ings of the Association for Computational Linguistics: EMNLP 2024, pages 14495–14508, Miami, Florida, USA. Association for Computational Linguistics. Zonglin Yang, Xinya Du, Alexander Rush, and Claire Cardie. 2020. Improving event duration prediction via time-awa...

work page arXiv 2024

[31] [31]

Which case law was applica- ble prior to the 2015 amendment of the privacy statute?

were introduced. Other strategies focused on enhancing recency- aware retrieval. Jatowt et al. (2005) proposed re- ranking methods using archived web snapshots to favor fresher content, while Dong et al. (2010) in- corporated real-time Twitter signals, and Setty et al. (2017) used news signals into crawling and rank- ing to support time-sensitive queries....

work page 2005

[32] [32]

What caused the economic crisis dur- ing Trump’s presidency?

and TOMATO (Shangguan et al., 2025) high- light the need for culturally and visually grounded temporal reasoning. Future research should fo- cus on developing multilingual temporal taggers, temporally annotated datasets in low-resource lan- guages, and cross-modal alignment techniques that jointly reason over text, images, and video to cap- ture time-rela...

work page 2025