A Hybrid Retrieval-Generation Neural Conversation Model

TL;DR

This paper introduces a hybrid neural conversation model that combines retrieval and generation techniques, resulting in more informative and coherent multi-turn dialogue systems, outperforming existing methods on social media datasets.

Contribution

The paper presents a novel hybrid model that integrates retrieval and generation approaches for neural conversation systems, improving response quality and diversity.

Findings

Outperforms pure retrieval and generation models on Twitter and Foursquare datasets.

Achieves higher scores on automatic and human evaluations.

Provides insights into combining retrieval and generation for better dialogue systems.

Abstract

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.