Relation Classification with Entity Type Restriction
Shengfei Lyu, Huanhuan Chen
Abstract
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. 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, RE-CENT, is model-agnostic. Based on two representative models GCN and SpanBERT respectively, RECENT GCN and RECENT SpanBERT are trained in RECENT 1 . Experimental results on a standard dataset indicate that RECENT improves the performance of GCN and Span-BERT by 6.9 and 4.4 F1 points, respectively. Especially, RECENT SpanBERT achieves a new state-of-the-art on TACRED.