Only One Relation Possible? Modeling the Ambiguity in Event Temporal Relation Extraction

TL;DR

This paper introduces a multi-label classification approach for Event Temporal Relation Extraction that better models ambiguity by considering multiple possible relations simultaneously, improving accuracy over traditional single-label methods.

Contribution

The paper proposes a novel multi-label classification framework with a speculation mechanism to handle ambiguous 'Vague' cases in ETRE, outperforming existing methods.

Findings

Improved recognition of specific temporal relations.

Effective utilization of 'Vague' instances.

Outperforms most state-of-the-art methods.

Abstract

Event Temporal Relation Extraction (ETRE) aims to identify the temporal relationship between two events, which plays an important role in natural language understanding. Most previous works follow a single-label classification style, classifying an event pair into either a specific temporal relation (e.g., \textit{Before}, \textit{After}), or a special label \textit{Vague} when there may be multiple possible temporal relations between the pair. In our work, instead of directly making predictions on \textit{Vague}, we propose a multi-label classification solution for ETRE (METRE) to infer the possibility of each temporal relation independently, where we treat \textit{Vague} as the cases when there is more than one possible relation between two events. We design a speculation mechanism to explore the possible relations hidden behind \textit{Vague}, which enables the latent information to be used efficiently. Experiments on TB-Dense, MATRES and UDS-T show that our method can effectively utilize the \textit{Vague} instances to improve the recognition for specific temporal relations and outperforms most state-of-the-art methods.