Browse State-of-the-Art › Temporal Relation Classification
Temporal Relation Classification
7 papers with code · 4 benchmarks · 5 datasets archive 2025-07-28
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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
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
Most implemented papers archive 2025-07-28
7 shown of 7 papers with code (27 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
14 Oct 2024 1 repository listed Syntology ran 5 of 6 samples · 1 unverifiedLarge Language Models (LLM) have recently shown promising performance in temporal reasoning tasks such as temporal question answering.
-
11 Jan 2023 1 repository listedAll in all, these problems have limited the fair comparison between approaches and consequently, the development of temporal extraction systems.
-
1 Oct 2022 1 repository listedThis 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 listedTo 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 listedEvent time is one of the most important features for event-event temporal relation extraction.
-
19 Apr 2021 1 repository listedExtracting temporal relations (e.
-
7 Aug 2018 1 repository listedIn this work, we extend our classification model's task loss with an unsupervised auxiliary loss on the word-embedding level of the model.
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. Read from the graph 2026-09-24.
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