Looking for the Bottleneck in Fine-grained Temporal Relation Classification
Hugo Sousa, Ricardo Campos, Alípio Jorge
TLDR
This paper introduces 'Interval from Point,' a novel method for fine-grained temporal relation classification that achieves state-of-the-art results.
Key contributions
- Revisits fine-grained temporal relation classification using the full set of interval relations between entities.
- Proposes 'Interval from Point' (IfP) method, classifying point relations between endpoints then decoding to interval relations.
- Achieves a new state-of-the-art temporal awareness score of 70.1% on the TempEval-3 benchmark.
Why it matters
This paper addresses the significant challenge of fine-grained temporal relation classification by tackling the full complexity of interval relations. Its novel 'Interval from Point' method provides a more robust and accurate approach, achieving state-of-the-art results and advancing temporal awareness in NLP.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.