Relational Graph Attention Network for Aspect-based Sentiment Analysis

By Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang. Annual Meeting of the Association for Computational Linguistics, 2020

698 citations recorded by the source corpus.

Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews. Most recent efforts adopt attention-based neural network models to implicitly connect aspects with opinion words. However, due to the complexity of language and the existence of multiple aspects in a single sentence, these models often confuse the connections. In this paper, we address this problem by means of effective encoding of syntax information. Firstly, we define a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree. Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction. Extensive experiments are conducted on the SemEval 2014 and Twitter datasets, and the experimental results confirm that the connections between aspects and opinion words can be better established with our approach, and the performance of the graph attention network (GAT) is significantly improved as a consequence.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8e85df955707cb7959299d83b6b8c8a28b2b53dd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Eduard H. Hovy
2. Hao Chen
3. Cuiping Li
4. Xiaojie Wang
5. Zhanyu Ma
6. Jing Zhang
7. Hong Chen
8. Haoyang Li

Citations in the corpus

• An Attentive Survey of Attention Models (2019, neutral): “Processing Machine Translation Zhang et al. [2020], Tang et al.”
• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, neutral): “• R-GAT [31] explores a relational graph attention network to encode the aspect-based tree structure for sentiment prediction.”
• RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL (2023, methodology): “Then, relation-aware transformer networks (Shaw, Uszkoreit, and Vaswani 2018) or relational graph neural networks, such as RGCN (Schlichtkrull et al. 2018) and RGAT (Wang et al. 2020b), are applied to encode each node.”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, methodology): “14) R-GAT+BERT (Wang et al., 2020) is the RGAT model that uses a pre-trained BERT to replace BiLSTM as an encoder.”