Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues

TL;DR

This paper introduces a novel transformer-based pseudo-Siamese network for planning dialogue paths in target-oriented proactive systems, improving response relevance and system effectiveness.

Contribution

It proposes the FF-BPSN model that combines bidirectional planning with forward focus, advancing dialogue path planning for proactive systems.

Findings

Achieves state-of-the-art in dialogue path planning on DuRecDial datasets.

Significantly improves response relevance in target-oriented dialogues.

Enhances overall system effectiveness in proactive dialogue tasks.

Abstract

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.