Title: Modeling Multi-Aspect Relationship with Joint Learning for Aspect-Level Sentiment Classification
Authors: Jie Zhou, Jimmy Xiangji Huang, Qinmin Vivian Hu and Liang He
Abstract: Aspect-level sentiment classification is a crucial branch for sentiment classification. Most of the existing work focuses on how to model the semantic relationship between the aspect and the sentence, while the relationships among the multiple aspects in the sentence is ignored. To address this problem, we propose a joint learning (Joint) model for aspect-level sentiment classification, which models the relationships among the aspects of the sentence and predicts the sentiment polarities of all aspects simultaneously. In particular, we first obtain the augmented aspect representation via an aspect modeling (AM) method. Then, we design a relationship modeling (RM) approach which transforms sentiment classification into a sequence labeling problem to model the potential relationships among each aspect in a sentence and predict the sentiment polarities of all aspects simultaneously. Extensive experiments on four benchmark datasets show that our approach can effectively improve the performance of aspect-level sentiment classification compared with the state-of-the-art approaches.
