Dongshi Ju


pdf bib
Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement
Dongshi Ju | Shi Feng | Pengcheng Lv | Daling Wang | Yifei Zhang
Proceedings of the 29th International Conference on Computational Linguistics

In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.