Browse State-of-the-Art › Temporal Relation Classification

Temporal Relation Classification

7 papers with code · 4 benchmarks · 5 datasets archive 2025-07-28

Natural Language Processing

Temporal Relation Classification is the task that is concerned with classifying the temporal relation between a pair of temporal entities (traditional events and temporal expressions). Initial approaches aimed to classify the temporal relation in thirteen relation types that were depicted by James Allen in his seminal work "Maintaining Knowledge about Temporal Intervals". However, due to the ambiguity in the annotation, recent corpora have been limiting the type of relations to a subset of those relations.

Notice that although Temporal Relation Classification can be thought of as a subtask of Temporal Relation Extraction, the two tasks can be morphed if one adds a label that indicates the absence of a temporal relation between the entities (e.g. "no_relation" or "vague") to Temporal Relation Classification.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MATRES (4 rows) RSGT RSGT: Relational Structure Guided Temporal Relation Extraction — — Compare
TB-Dense (3 rows) DTRE DCT-Centered Temporal Relation Extraction — — Compare
TDDAuto (3 rows) DTRE DCT-Centered Temporal Relation Extraction — — Compare
TDDMan (3 rows) DTRE DCT-Centered Temporal Relation Extraction — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 27 · with a code link: 7 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 27 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 27 of 27, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.

  • Large Language Models (LLM) have recently shown promising performance in temporal reasoning tasks such as temporal question answering.
  • 11 Jan 2023 1 repository listed
    All in all, these problems have limited the fair comparison between approaches and consequently, the development of temporal extraction systems.
  • 1 Oct 2022 1 repository listed
    This paper presents a comprehensive set of probing experiments using a multilingual language model, XLM-R, for temporal relation classification between events in four languages.
  • 2 Apr 2022 1 repository listed
    To achieve this goal, our work addresses the problems of subevent relation extraction (SRE) and temporal event relation extraction (TRE) that aim to predict subevent and temporal relations between two given event…
  • 1 Nov 2021 1 repository listed
    Event time is one of the most important features for event-event temporal relation extraction.
  • 19 Apr 2021 1 repository listed
    Extracting temporal relations (e. g., before, after, and simultaneous) among events is crucial to natural language understanding.
  • 7 Aug 2018 1 repository listed
    In this work, we extend our classification model's task loss with an unsupervised auxiliary loss on the word-embedding level of the model.
  • Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
    31 Oct 2023 0 repositories listed
    Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i.e. event, time, and document creation time (DCT).
  • 10 Oct 2022 0 repositories listed
    In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives.
  • 1 Oct 2022 0 repositories listed
    Most previous work on temporal relation extraction only focused on extracting the temporal relations among events or suffered from the issue of different expressions of events, timexes and Document Creation Time (DCT).
  • Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning
    1 Oct 2022 0 repositories listed
    “Event Temporal Relation Classification (ETRC) is crucial to natural language understanding.
  • 1 Oct 2022 0 repositories listed
    Temporal relation extraction aims to extract temporal relations between event pairs, which is crucial for natural language understanding.
  • 1 Aug 2021 0 repositories listed
    We present TIMERS - a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language.
  • TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events
    1 Sep 2019 0 repositories listed
    Prior work on temporal relation classification has focused extensively on event pairs in the same or adjacent sentences (local), paying scant attention to discourse-level (global) pairs.
  • Temporal Event Knowledge Acquisition via Identifying Narratives
    28 May 2018 0 repositories listed
    Inspired by the double temporality characteristic of narrative texts, we propose a novel approach for acquiring rich temporal "before/after" event knowledge across sentences in narrative stories.
  • A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events
    23 Jul 2017 0 repositories listed
    We present a sequential model for temporal relation classification between intra-sentence events.
  • Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths
    1 Jul 2017 0 repositories listed
    Temporal relation classification is becoming an active research field.
  • On the contribution of word embeddings to temporal relation classification
    1 Dec 2016 0 repositories listed
    Temporal relation classification is a challenging task, especially when there are no explicit markers to characterise the relation between temporal entities.
  • Temporal Relation Classification using a Model of Tense and Aspect
    1 Sep 2015 0 repositories listed
  • Exploiting Timegraphs in Temporal Relation Classification
    1 Oct 2014 0 repositories listed
  • Temporal Relation Classification in Persian and English contexts
    1 Sep 2013 0 repositories listed
  • UTTime: Temporal Relation Classification using Deep Syntactic Features
    1 Jun 2013 0 repositories listed
  • Temporal Relation Classification Based on Temporal Reasoning
    1 Mar 2013 0 repositories listed
  • Improved Temporal Relation Classification using Dependency Parses and Selective Crowdsourced Annotations
    1 Dec 2012 0 repositories listed
  • 16 Aug 2012 0 repositories listed
    The Spanish TimeBank Corpus contains 210 documents, which have been annotated with time and eventuality information according to the TimeML scheme, now accepted as an international cross-language ISO standard (ISO WD…
  • Aspectual Type and Temporal Relation Classification
    1 Apr 2012 0 repositories listed
  • SemEval-2010 Task 13: TempEval-2
    1 Jul 2010 0 repositories listed
    Tempeval-2 comprises evaluation tasks for time expressions, events and temporal relations, the latter of which was split up in four sub tasks, motivated by the notion that smaller subtasks would make both data…

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections