Learning bi-utterance for multi-turn response selection in retrieval-based chatbots

International Journal of Advanced Robotic Systems

ShuliangWang¹ 

关键词: Learning bi-utterance;    dialogue system;    deep learning;    information retrieval;   

DOI  :  10.1177/1729881419841930

学科分类：自动化工程

来源: InTech

【 摘 要 】

Multi-turn response selection is essential to retrieval-based chatbots. The task requires multi-turn response selection model to match a response candidate with a conversation context. Existing methods may lose relationship features in the context. In this article, we propose an improved method that extends the learning granularity of the multi-turn response selection model to enhance the model’s ability to learn relationship features of utterances in the context, which is a key to understand a conversation context for multi-turn response selection in retrieval-based chatbots. The experimental results show that our proposed method significantly improves sequential matching network for multi-turn response selection in retrieval-based chatbots.

【 授权许可】

CC BY