Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

TL;DR

This paper introduces an ensemble approach combining retrieval- and generation-based dialog systems, enhancing open-domain conversation quality by leveraging both methods and reranking to produce more relevant responses.

Contribution

The paper presents a novel ensemble framework that integrates retrieval and generation methods, improving response quality in open-domain dialog systems.

Findings

Ensemble outperforms individual retrieval or generation systems significantly.

Reranking with generated replies improves response relevance.

The approach achieves higher user satisfaction in experiments.

Abstract

Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (called a query) in a large database, and return a reply that best matches the query. Generative approaches, typically based on recurrent neural networks (RNNs), can synthesize new replies, but they suffer from the problem of generating short, meaningless utterances. In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain. In our approach, the retrieved candidate, in addition to the original query, is fed to an RNN-based reply generator, so that the neural model is aware of more information. The generated reply is then fed back as a new candidate for post-reranking. Experimental results show that such ensemble outperforms each single part of it by a large margin.