HAG: Hierarchical Attention with Graph Network for Dialogue Act Classification in Conversation

The prediction of Japanese dialogue acts (DA) labels requires context- and speaker-aware semantic comprehension. In this study, we proposed a hierarchical attention with the graph neural network (HAG) to consider the contextual interconnections and the semantics carried by the sentence itself. Concretely, the model use long-short term memory networks (LSTMs) to perform a context-aware encoding within a dialogue window. Then, we construct the context graph by aggregating the neighboring utterances. Subsequently, a speaker feature transformation is executed with a graph attention network (GAT) to calculate the interconnections, while a context-level feature selection is performed with a gated graph convolutional network (GatedGCN) to select the salient utterances that contribute to the DA classification. Finally, we merge the representations of different levels and conduct a classification with two dense layers. The experimental results show that our method outperforms the baselines.