Better Queries for Aspect-Category Sentiment Classification

Better Queries for Aspect-Category Sentiment Classification Yuncong Li 1, ∗, Cunxiang Yin1, ∗, Sheng-hua Zhong2, †, Huiqiang Zhong1, Jinchang Luo1, Siqi Xu1and Xiaohui Wu1 1Baidu Inc., Beijing, China 2College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China 1{liyuncong,yincunxiang,zhonghuiqiang,luojinchang,xusiqi01, wuxiaohui02}@baidu.com 2csshzhong@szu.edu.cn Abstract Aspect-category sentiment classification (ACSC) aims to identify the sentiment polarities to- wards the aspect categories mentioned in a sentence. Because a sentence often mentions more than one aspect category and expresses different sentiment polarities to them, finding aspect category-related information from the sentence is the key challenge to accurately recognize the sentiment polarity. Most previous models take both sentence and aspect category as input and query aspect category-related information based on the aspect category. However, these models represent the aspect category as a context-independent vector called aspect embedding, which may not be effective enough as a query. In this paper, we propose two contextualized aspect category representations, Contextualized Aspect Vector (CAV) and Contextualized Aspect Ma- trix (CAM). Specifically, we use the coarse aspect category-related information found by the aspect category detection task to generate CAV or CAM. Then the CAV or CAM as queries are used to search for fine-grained aspect category-related information like aspect embedding by aspect-category sentiment classification models. In experiments, we integrate the proposed CAV and CAM into several representative aspect embedding-based aspect-category sentiment classi- fication models. Experimental results on the SemEval-2014 Restaurant Review dataset and the Multi-Aspect Multi-Sentiment dataset demonstrate the effectiveness of CAV and CAM. 1 Introduction Sentiment analysis (Pang and Lee, 2008; Liu, 2012) is an important task in Natural Language Processing (NLP). It deals with the computational treatment of opinion, sentiment, and subjectivity in text. Aspect- based sentiment analysis (Pontiki et al., 2014; Pontiki et al., 2015; Pontiki et al., 2016) is a branch of sentiment analysis and aspect-category sentiment analysis (ACSA) is a subtask of it. In ACSA, there are a predefined set of aspect categories, and a predefined set of sentiment polarities. Given a sentence, the task aims to predict the aspect categories mentioned in the sentence and the corresponding sentiments. Therefore, ACSA contains two subtasks: aspect category detection (ACD) that detects aspect categories in a sentence and aspect-category sentiment classification (ACSC) that categorizes the sentiment po- larities with respect to the detected aspect categories. Figure 1 shows an example, “Staffs are not that friendly, but the taste covers all.”. ACD detects the sentence mentions two aspect categories: service and food, and ACSC predicts the sentiment polarities to them: negative and positive respectively. In this work, we focus on ACSC, while ACD as an auxiliary task is used to find coarse aspect category-related information for the ACSC task. Because a sentence often mentions more than one aspect category and expresses different sentiment polarities to them, to accurately recognize the sentiment polarities, most previous models (Ruder et al., 2016; Wang et al., 2016; Cheng et al., 2017; Li et al., 2017; Tay et al., 2018; Xue and Li, 2018; Xing et al., 2019; Liang et al., 2019b; Jiang et …

Content truncated to 500 words