An Embarrassingly Simple Model for Dialogue Relation Extraction
This work provides a more efficient and effective method for extracting relations between entities in dialogues, which is beneficial for natural language understanding systems.
This paper addresses dialogue relation extraction by proposing SimpleRE, a model that uses a novel input format called BERT Relation Token Sequence (BRS) to capture interrelations among multiple relations. SimpleRE achieves state-of-the-art performance on the DialogRE dataset with significantly reduced training time and outperforms baselines on sentence-level RE.
Dialogue relation extraction (RE) is to predict the relation type of two entities mentioned in a dialogue. In this paper, we propose a simple yet effective model named SimpleRE for the RE task. SimpleRE captures the interrelations among multiple relations in a dialogue through a novel input format named BERT Relation Token Sequence (BRS). In BRS, multiple [CLS] tokens are used to capture possible relations between different pairs of entities mentioned in the dialogue. A Relation Refinement Gate (RRG) is then designed to extract relation-specific semantic representation in an adaptive manner. Experiments on the DialogRE dataset show that SimpleRE achieves the best performance, with much shorter training time. Further, SimpleRE outperforms all direct baselines on sentence-level RE without using external resources.