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

Abstract

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.

Cite

Text

Wu et al. "Learn from Syntax: Improving Pair-Wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/545

Markdown

[Wu et al. "Learn from Syntax: Improving Pair-Wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/wu2021ijcai-learn/) doi:10.24963/IJCAI.2021/545

BibTeX

@inproceedings{wu2021ijcai-learn,
  title     = {{Learn from Syntax: Improving Pair-Wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge}},
  author    = {Wu, Shengqiong and Fei, Hao and Ren, Yafeng and Ji, Donghong and Li, Jingye},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {3957-3963},
  doi       = {10.24963/IJCAI.2021/545},
  url       = {https://mlanthology.org/ijcai/2021/wu2021ijcai-learn/}
}