Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 1986–1997 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 1986 Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction Junfeng Jiang∗ The University of Tokyo Tokyo, Japan jiangjf@is.s.u-tokyo.ac.jp An Wang∗ Tokyo Institute of Technology Tokyo, Japan wang.a.aa@m.titech.ac.jp Akiko Aizawa† National Institute of Informatics Tokyo, Japan aizawa@nii.ac.jp Abstract Target-oriented opinion words extraction (TOWE) is a subtask of aspect-based sen- timent analysis (ABSA). It aims to extract the corresponding opinion words for a given opinion target in a review sentence. Intuitively, the relation between an opinion target and an opinion word mostly relies on syntactics. In this study, we design a directed syntactic dependency graph based on a dependency tree to establish a path from the target to acandidate opinions. Subsequently, we propose novel attention-based relational graph convolutional neural network (ARGCN) to exploit syntactic information over dependency graphs. Moreover, to explicitly extract the corresponding opinion words toward the given opinion target, we effectively encode target in- formation in our model with the target-aware representation. Empirical results demonstrate that our model significantly outperforms all of the existing models on four benchmark datasets. Extensive analysis also demonstrates the effectiveness of each component of our models. Our code is available at https: //github.com/wcwowwwww/towe-eacl. 1 Introduction Target-oriented opinion words extraction (TOWE) (Fan et al., 2019) is a subtask of aspect-based senti- ment analysis (ABSA) (Hu and Liu, 2004; Pontiki et al., 2016). Given a review and an opinion target in the sentence, the objective of TOWE is to ex- tract the corresponding opinion words describing or evaluating the opinion targets from the review. Opinion targets are the words or phrases represent- ing features or entities toward which users express their attitudes, whereas opinion words referring to *These authors contributed equally to this work; the order is random. †Corresponding author. those terms are used to express attitudes or opinions explicitly. The food is tasty and portion sizes are appropriate. Target: food Opinion: tasty The food is tasty and portion sizes are appropriate. Target: portion size Opinion: appropriate Figure 1: Examples of TOWE task. The words high- lighted in orange represent the given opinion targets, whereas the words in blue represent the corresponding opinion words. Figure 1 shows two examples of TOWE. In the review “The food is tasty and portion sizes are appropriate .”, the terms “food” and “portion sizes” are two given opinion targets. TOWE needs to extract the word “tasty” as the opinion word for the opinion target “food” and the opinion word “appropriate” for the opinion target “portion sizes”. Therefore, the first challenge is to effectively introduce the opinion target information into our model. Fan et al. (2019) designed the IO-BiLSTM to encode the context before and after the given opinion targets separately to represent the position of the existing opinion targets. Wu et al. (2020) introduced position embeddings based on the rel- ative distance toward opinion targets. However, both studies only introduce parts of …

Content truncated to 500 words