Sentence-Level Relation Extraction via Contrastive Learning with Descriptive Relation Prompts
This work addresses a limitation in existing relation extraction methods by incorporating background knowledge and entity-relation interrelations, offering a novel approach for natural language processing tasks.
The paper tackled sentence-level relation extraction by proposing a new paradigm, Contrastive Learning with Descriptive Relation Prompts (CTL-DRP), which jointly considers entity information, relational knowledge, and entity type restrictions, achieving state-of-the-art F1-scores of 85.8% on TACREV and 91.6% on Re-TACRED.
Sentence-level relation extraction aims to identify the relation between two entities for a given sentence. The existing works mostly focus on obtaining a better entity representation and adopting a multi-label classifier for relation extraction. A major limitation of these works is that they ignore background relational knowledge and the interrelation between entity types and candidate relations. In this work, we propose a new paradigm, Contrastive Learning with Descriptive Relation Prompts(CTL-DRP), to jointly consider entity information, relational knowledge and entity type restrictions. In particular, we introduce an improved entity marker and descriptive relation prompts when generating contextual embedding, and utilize contrastive learning to rank the restricted candidate relations. The CTL-DRP obtains a competitive F1-score of 76.7% on TACRED. Furthermore, the new presented paradigm achieves F1-scores of 85.8% and 91.6% on TACREV and Re-TACRED respectively, which are both the state-of-the-art performance.