Novel target attention convolutional neural network for relation classification

Relation classification (RC) is an essential task in natural language processing (NLP), which extracts relationships of entity pairs in sentences of text. In the paper, a novel target attention convolutional neural network (TACNN) is proposed for the RC by fully utilizing word embedding information and position embedding information. Simultaneously, a target attention mechanism (TAM) is applied into a context layer of the convolutional neural network (CNN) model, which increases the effect of the relationship matrix weights of two entities in the sentence, while ignoring the calculation of irrelevant terms. And the TACNN is essentially to modify the weight of the relationship matrix of entities in the sentence at the context layer and connect the relationship feature composed of the lexical layer feature with the target attention layer feature. Therefore, the TACNN simplifies the structure of the CNN and improves the computational efficiency. On SemEval-2010 Task 8 dataset and Conll04 dataset, the TACNN obtains 85.3% and 71.4% of the F1-score, respectively. In contrast to previously available public models, the TACNN achieves a state-of-theart level in the F1-score of the RC.(c) 2022 Elsevier Inc. All rights reserved.

Automated summary

This paper proposes a novel target attention convolutional neural network (TACNN) for relation classification task, which fully utilizes word embedding and position embedding information to extract relationships between entity pairs in textual sentences. By applying the target attention mechanism in the context layer of the convolutional neural network model, the influence of the relationship matrix weights of entity pairs in the sentence is enhanced, while the calculation of irrelevant terms is ignored. In experiments, TACNN achieves high F1 scores on two datasets, surpassing the performance of previously available public models.