A Knowledge Driven Dialogue Model With Reinforcement Learning

Yongnan Jia

doi:10.1109/ACCESS.2020.2993924

2020-01-01

DOI：10.1109/ACCESS.2020.2993924

原文链接

查看原文

摘要

En 中文

In recent decades, many researchers pay a lot of attention on generating informative responses in end-to-end neural dialogue systems. In order to output the responses with knowledge and fact, many works leverage external knowledge to guide the process of response generation. However, human dialogue is not a simple sequence to sequence task but a process heavily relying on their background knowledge about the topic. Thus, the key of generating informative responses is leveraging the appropriate knowledge associated with current topic. This paper focus on addressing incorporating the appropriate knowledge in response generation. We adopt the reinforcement learning to select the most proper knowledge as the input information of the response generation part. Then we design an end-to-end dialogue model consisting of the knowledge decision part and the response generation part. The proposed model is able to effectively complete the knowledge driven dialogue task with specific topic. Our experiments clearly demonstrate the superior performance of our model over other baselines.

Keyword:

Learning (artificial intelligence)

Task analysis

Knowledge engineering

Decision making

Information retrieval

Computational modeling

Cognition

Dialogue model

policy gradient

knowledge graph

transformer network