Aspect-based Sentiment Analysis with Dependency Relation Graph Convolutional Network

Abstract

Aspect-based sentiment analysis (ABSA) aims to judge the sentiment polarity of specific aspects in text reviews, and is a fine-grained sentiment analysis task. In the current e-commerce era, ABSA based on user reviews is of great significance to consumers, producers and sellers. In order to make full use of the dependency information in the text, we propose a dependency graph convolutional network model for ABSA. Two graph convolutional networks are used to encode the dependency edge and the dependency tag respectively, and then a biaffine module is used to realize the interaction between the two. The experimental results show that the proposed model outperforms all other comparison models on 8 datasets in Chinese and English, including CMPR, SemEval 2014 Task4, Twitter, etc.