Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification

Aspect-based sentiment classification aims to predict the sentiment polarity of specific aspects appeared in a sentence. Nowadays, most current methods mainly focus on the semantic information by exploiting traditional attention mechanisms combined with recurrent neural networks to capture the interaction between the contexts and the targets. However, these models did not consider the importance of the relevant syntactical constraints. In this paper, we propose to employ a novel gated graph convolutional networks on the dependency tree to encode syntactical information, and we design a Syntax-aware Context Dynamic Weighted layer to guide our model to pay more attention to the local syntax-aware context. Moreover, Multi-head Attention is utilized for capturing both semantic information and interactive information between semantics and syntax. We conducted experiments on five datasets and the results demonstrate the effectiveness of the proposed model.