TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition

TL;DR

TransESC introduces a novel approach to emotion support conversation by modeling turn-level state transitions across semantics, strategy, and emotion to generate smoother, more natural, and supportive responses, validated by both automatic and human evaluations.

Contribution

It proposes a turn-level state transition modeling framework for ESC, incorporating semantics, strategy, and emotion transitions to improve response smoothness and effectiveness.

Findings

TransESC outperforms baselines in automatic evaluations.

Human assessments favor TransESC for response naturalness.

The method effectively captures fine-grained transition information.

Abstract

Emotion Support Conversation (ESC) is an emerging and challenging task with the goal of reducing the emotional distress of people. Previous attempts fail to maintain smooth transitions between utterances in ESC because they ignore to grasp the fine-grained transition information at each dialogue turn. To solve this problem, we propose to take into account turn-level state \textbf{Trans}itions of \textbf{ESC} (\textbf{TransESC}) from three perspectives, including semantics transition, strategy transition and emotion transition, to drive the conversation in a smooth and natural way. Specifically, we construct the state transition graph with a two-step way, named transit-then-interact, to grasp such three types of turn-level transition information. Finally, they are injected into the transition-aware decoder to generate more engaging responses. Both automatic and human evaluations on the benchmark dataset demonstrate the superiority of TransESC to generate more smooth and effective supportive responses. Our source code is available at \url{https://github.com/circle-hit/TransESC}.