---
title: "Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge"
authors:
  - "Shengqiong Wu"
  - "Hao Fei"
  - "Yafeng Ren"
  - "Donghong Ji"
  - "Jingye Li"
doi: "10.24963/ijcai.2021/545"
url: "https://ijcai.org/proceedings/2021/545"
pdf: "https://ijcai.org/proceedings/2021/0545.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3957-3963"
track: "Main Track"
keywords:
  - "Natural Language Processing: Natural Language Semantics"
  - "Natural Language Processing: Information Extraction"
  - "Natural Language Processing: Sentiment Analysis and Text Mining"
---

# 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*, pages 3957-3963. DOI: [10.24963/ijcai.2021/545](https://doi.org/10.24963/ijcai.2021/545)

## 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.