Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue

TL;DR

This paper introduces a policy-driven framework for document-grounded dialogue that improves knowledge selection and response generation by leveraging dialogue policies based on utterance function and topic transfer intent.

Contribution

It proposes a novel dialogue policy framework that enhances understanding and response quality in document-grounded dialogue tasks, achieving state-of-the-art results.

Findings

Achieved state-of-the-art performance on three benchmarks.

Demonstrated effectiveness of dialogue policy signals in knowledge selection.

Provided detailed analysis of policy impact on dialogue quality.

Abstract

Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper, we propose using a dialogue policy to help the dialogue understanding in DGD. Our dialogue policy consists of two kinds of guiding signals: utterance function and topic transfer intent. The utterance function reflects the purpose and style of an utterance, and the topic transfer intent reflects the topic and content of an utterance. We propose a novel framework exploiting our dialogue policy for two core tasks in DGD, namely knowledge selection (KS) and response generation (RG). The framework consists of two modules: the Policy planner leverages policy-aware dialogue representation to select knowledge and predict the policy of the response; the generator uses policy/knowledge-aware dialogue representation for response generation. Our policy-driven model gets state-of-the-art performance on three public benchmarks and we provide a detailed analysis of the experimental results. Our code/data will be released on GitHub.