Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge
This work addresses aspect-opinion extraction in natural language processing, which is important for sentiment analysis applications, but it appears incremental as it builds on existing methods with syntactic enhancements.
The paper tackles the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating syntactic knowledge through a syntax fusion encoder and high-order scoring methods, achieving state-of-the-art results on four benchmark datasets.
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.