Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1805–1815 June 6–11, 2021. ©2021 Association for Computational Linguistics 1805 Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction Yuhao Feng1, Yanghui Rao1,∗, Yuyao Tang2, Ninghua Wang2, He Liu2 1School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 2Tencent Inc, Shenzhen, China fengyh3@mail2.sysu.edu.cn; raoyangh@mail.sysu.edu.cn {youngtang,ninghuawang,heziliu}@tencent.com Abstract Opinion target extraction and opinion term extraction are two fundamental tasks in As- pect Based Sentiment Analysis (ABSA). Many recent works on ABSA focus on Target- oriented Opinion Words (or Terms) Extraction (TOWE), which aims at extracting the corre- sponding opinion words for a given opinion target. TOWE can be further applied to Aspect- Opinion Pair Extraction (AOPE) which aims at extracting aspects (i.e., opinion targets) and opinion terms in pairs. In this paper, we propose Target-Specified sequence label- ing with Multi-head Self-Attention (TSMSA) for TOWE, in which any pre-trained language model with multi-head self-attention can be in- tegrated conveniently. As a case study, we also develop a Multi-Task structure named MT- TSMSA for AOPE by combining our TSMSA with an aspect and opinion term extraction module. Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly; meanwhile, the perfor- mance of MT-TSMSA is similar or even better than state-of-the-art AOPE baseline models. 1 Introduction Aspect-Based Sentiment Analysis (ABSA) (Pon- tiki et al., 2014) has attracted much attention of researchers in recent years. In ABSA, aspect (or called opinion target) extraction and opinion term extraction are two fundamental tasks. Aspect is the word or phrase in the reviews referring to the object towards which users show attitudes, while opinion terms are those words or phrases represent- ing users’ attitudes (Wu et al., 2020). For example, in the sentence “The dim sum is delicious.”, the phrase “dim sum” is an aspect and the word “de- licious” is an opinion term. See the upper part of Table 1 for more examples. Plenty of works based on neural networks have been done in both aspect ∗The corresponding author. Reviews: “Soooo great! The food is delicious and inexpensive, and the environment is in a nice. The only problem is that the soup and dessert are ordinary." Aspect-Opinion Pairs: food : [delicious, inexpensive] (one-to-many) environment : [nice] (one-to-one) soup, dessert : [ordinary] (many-to-one) Table 1: The upper part is a restaurant review and the lower part shows the corresponding aspect-opinion pairs. Extracted aspects and opinion terms are marked in red and blue, respectively. and opinion term extraction (Liu et al., 2015; Po- ria et al., 2016; Xu et al., 2018); moreover, some studies combine these two tasks into a multi-task structure to extract aspects and opinion terms simul- taneously (Wang et al., 2016, 2017; Li and Lam, 2017; Dai and Song, 2019). However, one critical deficiency in the re- searches mentioned above is that they ignore the relation of aspects and opinion terms, which leads to the birth of Target-oriented Opinion Words (or …

Content truncated to 500 words