HAIN: Multilabel Classification With Hierarchical Attention-Based Interaction Network for Multiturn Dialogue Texts
Bin Cao, Kai Wang, Kui Ma, Jing Fan, Rui Yan, Yueshen Xu · IEEE Transactions on Cognitive and Developmental Systems · 2022
Multiturn dialogue systems with cognitive capabilities have been popularly used in many applications and generate a large volume of dialogue texts. The dialogue texts of many dialogue systems contain multiple labels, and a typical case is that the customer requirements or complaints in an online multiturn dialogue service system often need to be classified into multiple categories or forwarded to multiple departments, that is, multilabel classification on multiturn dialogue texts. Traditional methods treat the dialogue text as the plain text, which makes it difficult for classifiers to learn important features. On the other hand, regarding each utterance as the basic semantic unit may destroy the semantic information integrity of the dialogue. Furthermore, the above methods all ignore the relationship between labels. To address above issues, we propose to use the utterance pair as the basic semantic unit and design a novel multilabel classification model for multiturn dialogue texts in this article. Specifically, we propose to use the multihead attention mechanism to learn the key features of multiple labels and design a new method to learn the correlation among labels. Besides, we propose to use the penalty term to allow multihead attention to focus on different semantics. Finally, we conduct sufficient experiments on four real-world multiturn dialogue data sets and the experimental results show that our model produces superior performance.