Word Order is Considerable: Contextual Position-aware Graph Neural Network for Text Classification

Text Classification is a crucial and classical research branch in Natural Language Processing. Recently, Graph Neural Networks (GNNs) have been explored for this task since GNNs are proficient in handling non-Euclidean data with more complex relations. Despite the success, these graph-based methods have some limitations to model the word order information in the document. In this paper, to address this issue, we propose the Contextual Position-aware Graph Neural Network for text classification, which includes the Position-aware Graph Attention module and the Contextual Fusion module. The former can respectively capture left-side, self-side, and right-side word order information of each word. The latter enables the Context-fused Graph LSTM to learn word contextual representations by controlling three contextual information flows. In addition, experimental results have demonstrated that our proposed method can effectively enhance text representations, thus improving the classification performance.