Looking for the Bottleneck in Fine-grained Temporal Relation Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910170113638400 |
|---|---|
| author | Sousa, Hugo Campos, Ricardo Jorge, Alípio |
| author_facet | Sousa, Hugo Campos, Ricardo Jorge, Alípio |
| contents | Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text.
Despite recent advancements in natural language processing, temporal relation classification remains a considerable challenge.
Early attempts framed this task using a comprehensive set of temporal relations between events and temporal expressions.
However, due to the task complexity, datasets have been progressively simplified, leading recent approaches to focus on the relations between event pairs and to use only a subset of relations.
In this work, we revisit the broader goal of classifying interval relations between temporal entities by considering the full set of relations that can hold between two time intervals.
The proposed approach, Interval from Point, involves first classifying the point relations between the endpoints of the temporal entities and then decoding these point relations into an interval relation.
Evaluation on the TempEval-3 dataset shows that this approach can yield effective results, achieving a temporal awareness score of $70.1$ percent, a new state-of-the-art on this benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24620 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Looking for the Bottleneck in Fine-grained Temporal Relation Classification Sousa, Hugo Campos, Ricardo Jorge, Alípio Computation and Language Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advancements in natural language processing, temporal relation classification remains a considerable challenge. Early attempts framed this task using a comprehensive set of temporal relations between events and temporal expressions. However, due to the task complexity, datasets have been progressively simplified, leading recent approaches to focus on the relations between event pairs and to use only a subset of relations. In this work, we revisit the broader goal of classifying interval relations between temporal entities by considering the full set of relations that can hold between two time intervals. The proposed approach, Interval from Point, involves first classifying the point relations between the endpoints of the temporal entities and then decoding these point relations into an interval relation. Evaluation on the TempEval-3 dataset shows that this approach can yield effective results, achieving a temporal awareness score of $70.1$ percent, a new state-of-the-art on this benchmark. |
| title | Looking for the Bottleneck in Fine-grained Temporal Relation Classification |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.24620 |