An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.

Yiping Song, Rui Yan, Cheng-Te Li, Jian-Yun Nie, Ming Zhang, Dongyan Zhao

Abstract: Human-computer conversation systems have attracted much attention in Natural Language Processing. Conversation systems can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (namely a query) in a large conversational repository and return a reply that best matches the query. Generative approaches synthesize new replies. Both ways have certain advantages but suffer from their own disadvantages. We propose a novel ensemble of retrieval-based and generation-based conversation system. The retrieved candidates, in addition to the original query, are fed to a reply generator via a neural network, so that the model is aware of more information. The generated reply together with the retrieved ones then participates in a re-ranking process to find the final reply to output. Experimental results show that such an ensemble system outperforms each single module by a large margin.

TL;DR: A novel ensemble of retrieval-based and generation-based for open-domain conversation systems.

Keywords: conversation systems, retrieval method, generation method