Aspect-gated graph convolutional networks for aspect-based sentiment analysis

Aspect-based sentiment analysis aims to predict the sentiment polarity of each specific aspect term in a given sentence. However, the previous models ignore syntactical constraints and long-range sentiment dependencies and mistakenly identify irrelevant contextual words as clues for judging aspect sentiment. In addition, these models usually use aspect-independent encoders to encode sentences, which can lead to a lack of aspect information. In this paper, we propose an aspect-gated graph convolutional network (AGGCN), that includes a special aspect gate designed to guide the encoding of aspect-specific information from the outset and construct a graph convolution network on the sentence dependency tree to make full use of the syntactical information and sentiment dependencies. The experimental results on multiple SemEval datasets demonstrate the effectiveness of the proposed approach, and our model outperforms the strong baseline models.

Automated summary

This study introduces an aspect-gated graph convolutional network (AGGCN) with a special aspect gate designed to guide the encoding of aspect-specific information from the beginning. It constructs a graph convolution network on the sentence dependency tree to fully utilize syntactical information and sentiment dependencies, outperforming strong baseline models in sentiment analysis tasks.