Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialogue

TL;DR

This paper introduces a novel sequential topic selection model with a latent variable that leverages global conversation data to improve topic prediction and response generation in topic-grounded dialogue systems.

Contribution

It proposes a new model called Sequential Global Topic Attention (SGTA) that exploits cross-conversation topic transitions using a latent space with a skew-normal distribution.

Findings

Outperforms baseline models in topic prediction accuracy

Enhances response relevance and coherence in dialogue generation

Demonstrates effectiveness through extensive experiments

Abstract

Recently, topic-grounded dialogue system has attracted significant attention due to its effectiveness in predicting the next topic to yield better responses via the historical context and given topic sequence. However, almost all existing topic prediction solutions focus on only the current conversation and corresponding topic sequence to predict the next conversation topic, without exploiting other topic-guided conversations which may contain relevant topic-transitions to current conversation. To address the problem, in this paper we propose a novel approach, named Sequential Global Topic Attention (SGTA) to exploit topic transition over all conversations in a subtle way for better modeling post-to-response topic-transition and guiding the response generation to the current conversation. Specifically, we introduce a latent space modeled as a Multivariate Skew-Normal distribution with hybrid kernel functions to flexibly integrate the global-level information with sequence-level information, and predict the topic based on the distribution sampling results. We also leverage a topic-aware prior-posterior approach for secondary selection of predicted topics, which is utilized to optimize the response generation task. Extensive experiments demonstrate that our model outperforms competitive baselines on prediction and generation tasks.