An Embarrassingly Simple Model for Dialogue Relation Extraction. (arXiv:2012.13873v2 [cs.CL] UPDATED)

Web: http://arxiv.org/abs/2012.13873

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 …

arxiv model