Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

TL;DR

This paper introduces a Hybrid Latent Variable (HLV) approach combining discrete and continuous variables to improve diversity, relevance, and coherence in open-domain dialogue generation, addressing limitations of previous variational models.

Contribution

The paper proposes a novel HLV method and a Conditional Hybrid Variational Transformer (CHVT) that effectively balance diversity and coherence in dialogue responses.

Findings

CHVT outperforms traditional models on diversity, relevance, and coherence metrics.

HLV improves response diversity without sacrificing relevance.

Applying HLV to pre-trained models enhances their dialogue generation capabilities.

Abstract

Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduce the coherence of generated responses. In this paper, we also found that discrete latent variables have difficulty capturing more diverse expressions. To tackle these problems, we combine the merits of both continuous and discrete latent variables and propose a Hybrid Latent Variable (HLV) method. Specifically, HLV constrains the global semantics of responses through discrete latent variables and enriches responses with continuous latent variables. Thus, we diversify the generated responses while maintaining relevance and coherence. In addition, we propose Conditional Hybrid Variational Transformer (CHVT) to construct and to utilize HLV with transformers for dialogue generation. Through fine-grained symbolic-level semantic information and additive Gaussian mixing, we construct the distribution of continuous variables, prompting the generation of diverse expressions. Meanwhile, to maintain the relevance and coherence, the discrete latent variable is optimized by self-separation training. Experimental results on two dialogue generation datasets (DailyDialog and Opensubtitles) show that CHVT is superior to traditional transformer-based variational mechanism w.r.t. diversity, relevance and coherence metrics. Moreover, we also demonstrate the benefit of applying HLV to fine-tuning two pre-trained dialogue models (PLATO and BART-base).