Autoencoding Improves Pre-trained Word Embeddings

Proceedings of the 28th International Conference on Computational Linguistics, pages 162–172 Barcelona, Spain (Online), December 8-13, 2020 162 METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis Bin Jiang1*, Jing Hou1, Wanyue Zhou1, Chao Yang1, Shihan Wang2 and Liang Pang3 1College of Computer Science and Electronic Engineering, Hunan University, China 2Intelligent Systems, Utrecht University, The Netherlands 3CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, China {jiangbin, houjing, zhouwanyue, yangchaoedu}@hnu.edu.cn s.wang2@uu.nl, pangliang@ict.ac.cn Abstract Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each spe- cific aspect in a given sentence. Existing researches have realized the importance of the aspect for the ABSA task and have derived many interactive learning methods that model context based on specific aspect. However, current interaction mechanisms are ill-equipped to learn complex sentences with multiple aspects, and these methods underestimate the representation learning of the aspect. In order to solve the two problems, we propose a mutual enhanced transformation network (METNet) for the ABSA task. First, the aspect enhancement module in METNet im- proves the representation learning of the aspect with contextual semantic features, which gives the aspect more abundant information. Second, METNet designs and implements a hierarchical structure, which enhances the representations of aspect and context iteratively. Experimental re- sults on SemEval 2014 Datasets demonstrate the effectiveness of METNet, and we further prove that METNet is outstanding in multi-aspect scenarios. 1 Introduction Aspect-based sentiment analysis (ABSA) aims to determine the orientation of sentiment expressed on each aspect in a sentence (Liu, 2012). For instance, in the sentence “Although the service is not that great, I still like the food”, the user mentions two aspects “service” and “food” and expresses negative sentiment and positive sentiment respectively. The ABSA task consists of two subtasks including aspect extraction and aspect sentiment classification (Zhang et al., 2018). In this paper, we assume that the aspects are given and only focus on the aspect sentiment classification task. In ABSA task, multiple aspects could appear in one sentence. When predicting the sentiment of current aspect, words related to other aspects with different sentiment tendencies maybe become noises. Therefore, how to effectively model the semantic relationship between given aspect and context words is an important challenge. The traditional methods mainly rely on manually designed features, which is labor-intensive, and this representation method almost reaches its performance bottleneck (Ma et al., 2017). Boosted by the recent development of deep learning techniques, some studies utilize attention mechanism to solve the above problems well, and many neural attention models have been proposed (Wang et al., 2016; Tang et al., 2016b; Chen et al., 2017; Ma et al., 2017). In these works, the model generally obtains the aspect representation first and then applies attention mechanism to extract the context features related to the given aspect for sentiment prediction. However, the attention mechanism has some drawbacks. When a sentence contains multiple aspects with different sentiment tendencies, opinion modifiers of other aspects are noise information for the …

Content truncated to 500 words