Incorporating Causal Analysis into Diversified and Logical Response Generation

TL;DR

This paper introduces a causal analysis-based approach to improve response relevance and logical consistency in dialogue generation, combining mediator prediction and a topic-guided CVAE model.

Contribution

It proposes a novel causal analysis framework and a TGG-CVAE model to enhance response relevance and reduce bias in dialogue systems.

Findings

Outperforms state-of-the-art models in automatic metrics

Generates more relevant and informative responses

Improves logical consistency in dialogue generation

Abstract

Although the Conditional Variational AutoEncoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question. A causal analysis is carried out to study the reasons behind, and a methodology of searching for the mediators and mitigating the confounding bias in dialogues is provided. Specifically, we propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediators into generating process. Besides, a dynamic topic graph guided conditional variational autoencoder (TGG-CVAE) model is utilized to complement the semantic space and reduce the confounding bias in responses. Extensive experiments demonstrate that the proposed model is able to generate both relevant and informative responses, and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.