用对话策略提升文档对话中的知识选择与回复生成效果
Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
- 引入话语功能与话题转移意图作为引导信号，增强对话理解
- 在三个公开数据集上达到当前最优性能，显著提升响应相关性
- 适合研究文档对话、对话系统优化的研究者与开发者
文档接地对话（DGD）利用文档作为外部知识支持对话生成。正确理解对话上下文对于从文档中选择知识并生成恰当回应至关重要。本文提出使用对话策略来辅助DGD中的对话理解。该对话策略包含两类引导信号：话语功能和话题转移意图。话语功能反映语句的目的与风格，话题转移意图反映语句的主题与内容。我们提出一种新框架，利用该对话策略解决DGD中的两个核心任务：知识选择（KS）与响应生成（RG）。该框架由两个模块组成：政策规划器利用策略感知的对话表示进行知识选择并预测响应策略；生成器则使用策略/知识感知的对话表示生成响应。所提出的策略驱动模型在三个公开基准上取得当前最优表现，并提供了详细的实验结果分析。代码与数据将发布于GitHub。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。