A Knowledge Driven Dialogue Model with Reinforcement Learning

Yongnan Jia, Gaochen Min, Cong Xu, Xisheng Li, Dezheng Zhang
2020 IEEE Access  
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
more » ... nowledge 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. INDEX TERMS Dialogue model, policy gradient, knowledge graph, transformer network. Recently, reseachers have begun to introduce external knowledge into open-domain chat conversations [4], [5]. Ghazvininejad et al. [6] proposed a knowledge-driven neural VOLUME 8, 2020 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
doi:10.1109/access.2020.2993924 fatcat:iqzjcl7erjbxrnyrx43kxfnjzy