Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection

TL;DR

This paper introduces a multi-mapping mechanism with posterior mapping selection to improve the generation of diverse, relevant responses in conversational models, addressing the challenge of accurately modeling one-to-many relationships.

Contribution

It proposes a novel multi-mapping framework with a posterior selection module and auxiliary loss for better response diversity and relevance in dialogue generation.

Findings

Outperforms state-of-the-art methods in response diversity

Generates more informative and relevant responses

Achieves superior results on benchmark datasets

Abstract

In human conversation an input post is open to multiple potential responses, which is typically regarded as a one-to-many problem. Promising approaches mainly incorporate multiple latent mechanisms to build the one-to-many relationship. However, without accurate selection of the latent mechanism corresponding to the target response during training, these methods suffer from a rough optimization of latent mechanisms. In this paper, we propose a multi-mapping mechanism to better capture the one-to-many relationship, where multiple mapping modules are employed as latent mechanisms to model the semantic mappings from an input post to its diverse responses. For accurate optimization of latent mechanisms, a posterior mapping selection module is designed to select the corresponding mapping module according to the target response for further optimization. We also introduce an auxiliary matching loss to facilitate the optimization of posterior mapping selection. Empirical results demonstrate the superiority of our model in generating multiple diverse and informative responses over the state-of-the-art methods.