Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
For researchers in dialogue systems, this work addresses the under-explored problem of planning dialogue paths toward predefined targets, offering a novel method that outperforms existing approaches.
The paper tackles dialogue path planning in target-oriented proactive dialogues, proposing a Forward-Focused Bidirectional Pseudo-Siamese Network (FF-BPSN) that achieves state-of-the-art performance on DuRecDial and DuRecDial 2.0, significantly enhancing system effectiveness.
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.