Multitask Learning Based on Constrained Hierarchical Attention Network for Multi-aspect Sentiment Classification

Abstract

Aspect-level sentiment classification (ALSC) aims to distinguish the sentiment polarity of each given aspect in text. A user-generated review usually contains several aspects with different sentiment for each aspect, but most existing approaches only identify one aspect-specific sentiment polarity. Moreover, the prior works using attention mechanisms will introduce inherent noise and reduce the performance of the work. Therefore, we propose a model called Multitask Learning based on Constrained HiErarchical ATtention network (ML-CHEAT), a simple but effective method, which uses the regularization unit to limit the attention weight of each aspect. In addition, the ML-CHEAT uses the hierarchical attention network to learn the potential relationship between aspect features and sentiment features. Furthermore, we extend our approach to multitask learning to optimize the parameters update in the backpropagation and improve the performance of the model. Experimental results on SemEval competition datasets demonstrate the effectiveness and reliability of our approach.

Supported by the National Natural Science Foundation of China (Grant Nos. 61872139, 61876062, 61702181), the Natural Science Foundation of Hunan Province (Grant No. 2018JJ3190) and the Scientific Research Fund of Hunan Provincial Education Department (Grant No. 18B199).