Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation

Amir Pouran Ben Veyseh,Thien Huu Nguyen,Dejing Dou,Franck Dernoncourt,Quan Hung Tran,Nasim Nouri

doi:10.18653/v1/2020.findings-emnlp.407

Abstract

Aspect-based Sentiment Analysis (ABSA) seeks to predict the sentiment polarity of a sentence toward a specific aspect. Recently, it has been shown that dependency trees can be integrated into deep learning models to produce the state-of-the-art performance for ABSA. However, these models tend to compute the hidden/representation vectors without considering the aspect terms and fail to benefit from the overall contextual importance scores of the words that can be obtained from the dependency tree for ABSA. In this work, we propose a novel graph-based deep learning model to overcome these two issues of the prior work on ABSA. In our model, gate vectors are generated from the representation vectors of the aspect terms to customize the hidden vectors of the graph-based models toward the aspect terms. In addition, we propose a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA. The proposed model achieves the state-of-the-art performance on three benchmark datasets.

Highlights

Aspect-based Sentiment Analysis (ABSA) is a finegrained version of sentiment analysis (SA) that aims to find the sentiment polarity of the input sentences toward a given aspect
We demonstrate the effectiveness of the proposed model with the state-of-the-art performance on three benchmark datasets for ABSA
To demonstrate the effectiveness of the proposed method, we compare it with the following baselines: (1) the feature-based model that applies feature engineering and the SVM model (Wagner et al, 2014), (2) the deep learning models based on the sequential order of the words in the sentences, including convolutional neural networks (CNN), LSTM, attention and the gating mechanism (Wagner et al, 2016; Wang et al, 2016; Tang et al, 2016; Huang et al, 2018; Jiang et al, 2019), and (3) the graph-based models that exploit dependency trees to improve the deep learning models for ABSA (Huang and Carley, 2019; Zhang et al, 2019; Hou et al, 2019; Sun et al, 2019; Wang et al, 2020)

Summary

Introduction

Aspect-based Sentiment Analysis (ABSA) is a finegrained version of sentiment analysis (SA) that aims to find the sentiment polarity of the input sentences toward a given aspect. We focus on the term-based aspects for ABSA where the aspects correspond to some terms (i.e., sequences of words) in the input sentence. Due to its important applications (e.g., for opinion mining), ABSA has been studied extensively in the literature. In these studies, deep learning has been employed to produce the state-of-the-art performance for this problem (Wagner et al, 2016; Dehong et al, 2017). Dependency trees help to directly link the aspect term to the syntactically related words in the sentence, facilitating the graph convolutional neural networks (GCN) (Kipf and Welling, 2017) to enrich the representation vectors for the aspect terms

Methods

Results

Conclusion