Personalized Dialogue Generation Model Based on BERT and Hierarchical Copy Mechanism  

作　　者：Zijian Liu Yan Peng Shifeng Ni Zijian Liu;Yan Peng;Shifeng Ni(School of Computer Science and Engineering, Sichuan University of Science and Engineering, Yibin, China)

机构地区：[1]School of Computer Science and Engineering, Sichuan University of Science and Engineering, Yibin, China

出　　处：《Journal of Computer and Communications》2022年第7期35-52,共18页电脑和通信（英文）

摘　　要：Despite the great advances in generative dialogue systems, existing dialogue generation models are still unsatisfactory in maintaining persona consistency. In order to make the dialogue generation model generate more persona-consistent responses, this paper proposes a model named BERT-HCM (Personalized Dialogue Generation Model Based on BERT and Hierarchical Copy Mechanism). The model uses an encoder based on BERT initialization to encode persona information and dialogue queries and subsequently uses a Transformer decoder incorporating a hierarchical copy mechanism to dynamically copy the input-side content to guide the model in generating responses. The experimental results show that the proposed model improves on both automatic and human evaluation metrics compared to the baseline model and is able to generate more fluent, relevant and persona-consistent responses.Despite the great advances in generative dialogue systems, existing dialogue generation models are still unsatisfactory in maintaining persona consistency. In order to make the dialogue generation model generate more persona-consistent responses, this paper proposes a model named BERT-HCM (Personalized Dialogue Generation Model Based on BERT and Hierarchical Copy Mechanism). The model uses an encoder based on BERT initialization to encode persona information and dialogue queries and subsequently uses a Transformer decoder incorporating a hierarchical copy mechanism to dynamically copy the input-side content to guide the model in generating responses. The experimental results show that the proposed model improves on both automatic and human evaluation metrics compared to the baseline model and is able to generate more fluent, relevant and persona-consistent responses.

关 键 词：Personalized Dialogue Generation BERT Hierarchical Copy Mechanism Persona Consistency 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]