Relation Classification with Entity Type Restriction
This addresses the issue of inappropriate candidate relations in relation classification for natural language processing tasks, offering a model-agnostic solution that enhances accuracy.
The paper tackles the problem of relation classification by proposing a novel paradigm, RECENT, which uses entity type restrictions to filter candidate relations, improving the performance of GCN and SpanBERT models by 6.9 and 4.4 F1 points, respectively, and achieving a new state-of-the-art on the TACRED dataset.
Relation classification aims to predict a relation between two entities in a sentence. The existing methods regard all relations as the candidate relations for the two entities in a sentence. These methods neglect the restrictions on candidate relations by entity types, which leads to some inappropriate relations being candidate relations. In this paper, we propose a novel paradigm, RElation Classification with ENtity Type restriction (RECENT), which exploits entity types to restrict candidate relations. Specially, the mutual restrictions of relations and entity types are formalized and introduced into relation classification. Besides, the proposed paradigm, RECENT, is model-agnostic. Based on two representative models GCN and SpanBERT respectively, RECENT_GCN and RECENT_SpanBERT are trained in RECENT. Experimental results on a standard dataset indicate that RECENT improves the performance of GCN and SpanBERT by 6.9 and 4.4 F1 points, respectively. Especially, RECENT_SpanBERT achieves a new state-of-the-art on TACRED.