EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction

Abstract

Multi-triple extraction is a challenging task due to the existence of informative inter-triple correlations and consequently rich interactions across the constituent entities and relations. While existing works only explore cross-entity interactions, we propose to explicitly introduce relation representation, jointly represent it with entities, and novelly align them to identify valid triples. We perform comprehensive experiments on document-level relation extraction and joint entity and relation extraction along with detailed ablations to demonstrate the advantage of the proposed method.

Tasks

Reproductions