Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge

Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge

Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, Jingye Li

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 3957-3963. https://doi.org/10.24963/ijcai.2021/545

In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion encoder for encoding syntactic features, including a label-aware graph convolutional network (LAGCN) for modeling the dependency edges and labels, as well as the POS tags unifiedly, and a local-attention module encoding POS tags for better term boundary detection. During pairing, we then adopt Biaffine and Triaffine scoring for high-order aspect-opinion term pairing, in the meantime re-harnessing the syntax-enriched representations in LAGCN for syntactic-aware scoring. Experimental results on four benchmark datasets demonstrate that our model outperforms current state-of-the-art baselines, meanwhile yielding explainable predictions with syntactic knowledge.
Keywords:
Natural Language Processing: Information Extraction
Natural Language Processing: Natural Language Semantics
Natural Language Processing: Sentiment Analysis and Text Mining