Recurrent neural network (RNN) and convolutional neural network (CNN) are two prevailing architectures used in text classification. Traditional approaches combine the strengths of these two networks by straightly streamlining them or linking features extracted from them. In this article, a novel approach is proposed to maintain the strengths of RNN and CNN to a great extent. In the proposed approach, a bi-directional RNN encodes each word into forward and backward hidden states. Then, a neural tensor layer is used to fuse bi-directional hidden states to get word representations. Meanwhile, a convolutional neural network is utilized to learn the importance of each word for text classification. Empirical experiments are conducted on several datasets for text classification. The superior performance of the proposed approach confirms its effectiveness.

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.

No abstract

No abstract

No abstract