Aspect and Opinion Term Extraction Using Graph Attention Network

TL;DR

This paper demonstrates that using a Graph Attention Network with dependency tree features significantly improves aspect and opinion term extraction accuracy, outperforming previous methods on standard datasets.

Contribution

The study introduces a novel application of Graph Attention Networks with dependency structures for token-level aspect and opinion extraction, enhancing performance over existing models.

Findings

Dependency structure as a feature improves extraction accuracy

The approach outperforms previous models on SemEval datasets

Works well with multiple aspects and sentiments in queries

Abstract

In this work we investigate the capability of Graph Attention Network for extracting aspect and opinion terms. Aspect and opinion term extraction is posed as a token-level classification task akin to named entity recognition. We use the dependency tree of the input query as additional feature in a Graph Attention Network along with the token and part-of-speech features. We show that the dependency structure is a powerful feature that in the presence of a CRF layer substantially improves the performance and generates the best result on the commonly used datasets from SemEval 2014, 2015 and 2016. We experiment with additional layers like BiLSTM and Transformer in addition to the CRF layer. We also show that our approach works well in the presence of multiple aspects or sentiments in the same query and it is not necessary to modify the dependency tree based on a single aspect as was the original application for sentiment classification.