Looking for the Bottleneck in Fine-grained Temporal Relation Classification

TL;DR

This paper introduces a new approach for classifying interval relations between temporal entities by analyzing endpoint point relations, achieving state-of-the-art results on the TempEval-3 dataset.

Contribution

It proposes the 'Interval from Point' method that classifies point relations first and then decodes them into interval relations, broadening the scope of temporal relation classification.

Findings

Achieved a 70.1% temporal awareness score on TempEval-3

Outperformed previous methods on the same benchmark

Demonstrated the effectiveness of point-based relation classification

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.