A Hybrid Retrieval-Generation Neural Conversation Model
This work addresses the challenge of building more effective multi-turn conversation systems for users, representing an incremental improvement by integrating existing approaches.
The paper tackles the problem of developing intelligent personal assistants by proposing a hybrid neural conversation model that combines retrieval-based and generation-based methods, achieving superior performance on Twitter and Foursquare data compared to existing methods in both automatic and human evaluations.
Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.