A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 5569–5580, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 5569 A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis Yunlong Liang1∗, Fandong Meng2, Jinchao Zhang2, Jinan Xu1† Yufeng Chen1 and Jie Zhou2 1Beijing Jiaotong University, China 2Pattern Recognition Center, WeChat AI, Tencent Inc, China {yunlonliang,jaxu,chenyf}@bjtu.edu.cn {fandongmeng,dayerzhang,withtomzhou}@tencent.com Abstract Aspect based sentiment analysis (ABSA) aims to identify the sentiment polarity towards the given aspect in a sentence, while pre- vious models typically exploit an aspect- independent (weakly associative) encoder for sentence representation generation. In this pa- per, we propose a novel Aspect-Guided Deep Transition model, named AGDT, which uti- lizes the given aspect to guide the sentence encoding from scratch with the specially- designed deep transition architecture. Fur- thermore, an aspect-oriented objective is de- signed to enforce AGDT to reconstruct the given aspect with the generated sentence rep- resentation. In doing so, our AGDT can ac- curately generate aspect-specific sentence rep- resentation, and thus conduct more accurate sentiment predictions. Experimental results on multiple SemEval datasets demonstrate the ef- fectiveness of our proposed approach, which significantly outperforms the best reported re- sults with the same setting.1 1 Introduction Aspect based sentiment analysis (ABSA) is a fine- grained task in sentiment analysis, which can pro- vide important sentiment information for other natural language processing (NLP) tasks. There are two different subtasks in ABSA, namely, aspect-category sentiment analysis and aspect- term sentiment analysis (Pontiki et al., 2014; Xue and Li, 2018). Aspect-category sentiment analy- sis aims at predicting the sentiment polarity to- wards the given aspect, which is in predefined sev- eral categories and it may not appear in the sen- tence. For instance, in Table 1, the aspect-category sentiment analysis is going to predict the senti- ment polarity towards the aspect “food”, which ∗ Work was done when Yunlong Liang was an intern at Pattern Recognition Center, WeChat AI, Tencent Inc, China. †Jinan Xu is the corresponding author. 1The code is publicly available at: https://github. com/XL2248/AGDT Sentence The appetizers are ok, but the service is slow. Aspect-Category food service Aspect-Term The appetizers service Sentiment Polarity Neutral Negative Table 1: The instance contains different sentiment po- larities towards two aspects. is not appeared in the sentence. By contrast, the goal of aspect-term sentiment analysis is to predict the sentiment polarity over the aspect term which is a subsequence of the sentence. For instance, the aspect-term sentiment analysis will predict the sentiment polarity towards the aspect term “The appetizers”, which is a subsequence of the sen- tence. Additionally, the number of categories of the aspect term is more than one thousand in the training corpus. As shown in Table 1, sentiment polarity may be different when different aspects are consid- ered. Thus, the given aspect (term) is crucial to ABSA tasks (Jiang et al., 2011; Ma et al., 2017; Wang et al., 2018; Xing et al., 2019; Liang …

Content truncated to 500 words