用双向伪孪生网络规划对话路径，提升目标导向主动对话效果
Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
- 设计双向伪孪生网络，前后向联合规划对话路径
- 在DuRecDial数据集上达到最优路径规划性能
- 适合需要精准引导对话的智能客服与推荐系统
目标导向的主动对话系统旨在引导对话向预设目标推进，并主动提出建议。其核心范式是规划合理的对话路径，再引导语言模型（如预训练或大语言模型）生成回应，其中对话路径规划是关键但尚未充分研究的问题。本文提出一种前向聚焦的双向伪孪生网络（FF-BPSN），采用两个相同的基于Transformer的解码器分别进行前向和后向规划，并通过前向聚焦模块融合双向信息，构建最终的前向路径。该路径兼顾双向规划优势，同时优先保留前向信息。随后，利用规划路径指导语言模型生成回复。在DuRecDial和DuRecDial 2.0上的大量实验表明，FF-BPSN在对话路径规划上达到当前最优性能，并显著提升了目标导向主动对话系统的有效性。
原文摘要 · Abstract (English)
A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core paradigm of such a system is to plan a reasonable dialogue path and subsequently guide language models (e.g., pre-trained or large language models) to generate responses, where dialogue path planning serves as the central component-a novel yet under-explored problem. In this work, we propose a Forward-Focused Bidirectional Pseudo-Siamese Network (FF-BPSN) for dialogue path planning toward predefined dialogue targets. FF-BPSN employs two identical transformer-based decoders for forward and backward planning, together with a forward-focused module that integrates bidirectional information to construct the final forward path. This path benefits from bidirectional planning while prioritizing forward information. We then employ the planned path to guide language models in response generation. Extensive experiments on DuRecDial and DuRecDial 2.0 demonstrate that FF-BPSN achieves state-of-the-art performance in dialogue path planning and significantly enhances the effectiveness of target-oriented proactive dialogue systems.
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。