Exploring fine-grained syntactic information for aspect-based sentiment classification with dual graph neural networks

The goal of aspect-based sentiment classification (ASC) is to predict the corresponding emotion of a speci-fic target of a sentence. In neural network-based methods for ASC, various sophisticated models such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) are widespread. Recently, ongoing research has integrated syntactic structures into graph neural networks (GNN) to deal with ASC tasks. However, these methods are limited due to the noise and inefficient use of information of syntactic dependency trees. This paper proposes a novel GNN based deep learning model to overcome the deficien-cies of prior studies. In the proposed model, to exploit the information in the syntactic dependency trees, a novel part-of-speech (POS) guided syntactic dependency graph is constructed for a relational graph attention network (RGAT) to eliminate the noises. Further, a syntactic distance attention-guided layer is designed for a densely connected graph convolutional network (DCGCN), which can fully extract semantic dependency between contextual words. Experiments on three public datasets are carried out to evaluate the effectiveness of the proposed model. Comparing to the baselines, our model, as a best alternative, achieves state-of-arts performance. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a novel GNN based deep learning model for aspect-based sentiment classification, which effectively utilizes syntactic structures and semantic dependencies between contextual words to achieve state-of-the-art performance.