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

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4543–4548 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4543 Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation Amir Pouran Ben Veyseh1∗, Nasim Nouri∗, Franck Dernoncourt2, Quan Hung Tran2, Dejing Dou1 and Thien Huu Nguyen1,3 1 Department of Computer and Information Science, University of Oregon, Eugene, OR 97403, USA 2 Adobe Research, San Jose, CA, USA 3 VinAI Research, Vietnam {apouranb,dou,thien}@cs.uoregon.edu, nasim.nourii@gmail.com, {dernonco,qtran}@adobe.com 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 com- pute 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 de- pendency tree for ABSA. In this work, we pro- pose a novel graph-based deep learning model to overcome these two issues of the prior work on ABSA. In our model, gate vectors are gen- erated 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 pro- posed model achieves the state-of-the-art per- formance on three benchmark datasets. 1 Introduction Aspect-based Sentiment Analysis (ABSA) is a fine- grained version of sentiment analysis (SA) that aims to find the sentiment polarity of the input sen- tences 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. For instance, an ABSA sys- tem should be able to return the negative sentiment for input sentence “The staff were very polite, but the quality of the food was terrible.” assuming “food” as the aspect term. Due to its important applications (e.g., for opin- ion mining), ABSA has been studied extensively ∗Equal contribution. 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). Recently, in order to further improve the performance, the syntactic dependency trees have been integrated into the deep learning models (Huang and Carley, 2019; Zhang et al., 2019) for ABSA (called the graph-based deep learn- ing models). Among others, dependency trees help to directly link the aspect term to the syntactically related words in the sentence, thus facilitating the graph convolutional neural networks (GCN) (Kipf and Welling, 2017) to enrich the representation vectors for the aspect terms. However, there are at least two major issues in these graph-based models that should be addressed to boost the performance. First, the representa- tion vectors for the words in different …

Content truncated to 500 words