Enhancing Aspect-level Sentiment Analysis with Word Dependencies

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 3726–3739 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 3726 Enhancing Aspect-level Sentiment Analysis with Word Dependencies Yuanhe Tian♥⇤, Guimin Chen~⇤, Yan Song♠~† ♥University of Washington ~Shenzhen Research Institute of Big Data ♠The Chinese University of Hong Kong (Shenzhen) ♥yhtian@uw.edu ~chenguimin@sribd.cn ♠songyan@cuhk.edu.cn Abstract Aspect-level sentiment analysis (ASA) has re- ceived much attention in recent years. Most existing approaches tried to leverage syntac- tic information, such as the dependency pars- ing results of the input text, to improve senti- ment analysis on different aspects. Although these approaches achieved satisfying results, their main focus is to leverage the dependency arcs among words where the dependency type information is omitted; and they model dif- ferent dependencies equally where the noisy dependency results may hurt model perfor- mance. In this paper, we propose an ap- proach to enhance aspect-level sentiment anal- ysis with word dependencies, where the type information is modeled by key-value memory networks and different dependency results are selectively leveraged. Experimental results on five benchmark datasets demonstrate the effec- tiveness of our approach, where it outperforms baseline models on all datasets and achieves state-of-the-art performance on three of them.1 1 Introduction Aspect-level sentiment analysis (ASA) determines the sentiment polarity of a given input text on the fine-grained level, where the sentiment towards a particular aspect in the text is predicted instead of the entire input. E.g., the sentiment of an aspect “bar service” in the sentence “Total environment is fantastic although bar service is poor.” is nega- tive, although the text as a whole conveys a positive sentiment polarity. Due to its high practical value in many scenarios, e.g., product review analysis, social media tracking, etc., ASA attracts much at- tention in the natural language processing (NLP) community for years (Tang et al., 2016a,b; He et al., 2018a; Sun et al., 2019; Zhang et al., 2019; Song et al., 2019; Huang and Carley, 2019). *Equal contribution. †Corresponding author. 1The code and different models are released at https: //github.com/cuhksz-nlp/ASA-WD. In recent studies, neural networks, especially recurrent models with attention mechanism, are widely applied in this task, where many of them (Wang et al., 2016; Tang et al., 2016a; Chen et al., 2017; Ma et al., 2017; Fan et al., 2018; Liang et al., 2019; Tang et al., 2020) model semantic related- ness between context and aspect words to facili- tate sentiment analysis on aspects. There are other approaches using additional inputs such as word position (Gu et al., 2018), document information (He et al., 2018b; Li et al., 2018a), commonsense knowledge (Ma et al., 2018). Among all such in- puts, dependency results of the input text are proved to be a kind of useful information (He et al., 2018a; Sun et al., 2019; Huang and Carley, 2019; Zhang et al., 2019; Wang et al., 2020; Tang et al., 2020), because they can help the model locate important content that modifies the aspect words and thus …

Content truncated to 500 words