TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues

TL;DR

This paper introduces TREND, a relation-extraction network that leverages trigger identification to improve dialogue relation extraction, demonstrating transferability across datasets and domains.

Contribution

The paper proposes a novel trigger-enhanced relation extraction model that learns trigger identification and transfers this knowledge to enhance performance on unseen relations.

Findings

Improves relation extraction accuracy on unseen relations

Demonstrates effective transfer of trigger-finding across datasets

Enhances performance in multi-domain dialogue scenarios

Abstract

The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue. During conversations, speakers may expose their relations to certain entities by explicit or implicit clues, such evidences called "triggers". However, trigger annotations may not be always available for the target data, so it is challenging to leverage such information for enhancing the performance. Therefore, this paper proposes to learn how to identify triggers from the data with trigger annotations and then transfers the trigger-finding capability to other datasets for better performance. The experiments show that the proposed approach is capable of improving relation extraction performance of unseen relations and also demonstrate the transferability of our proposed trigger-finding model across different domains and datasets.