Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations

2026-04-20

AI Summary

This work addresses the challenge of fine-grained next-turn dialogue act prediction in counseling conversations, which is hindered by data sparsity and inadequate modeling of conversational flow. To overcome these limitations, the authors propose a lightweight regularization method that incorporates dialogue act transition priors derived from corpus statistics. Specifically, they impose a KL divergence constraint on model predictions to explicitly inject knowledge of conversational dynamics. The approach yields substantial performance gains for weak baselines under low-resource, fine-grained settings, achieving relative macro-F1 improvements of 9%–42% across 60 German counseling dialogue act classes. Further cross-lingual and cross-domain experiments demonstrate the method’s strong generalization capabilities.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is proposed that aligns predicted act distributions with corpus-derived transition patterns. Evaluated on a 60-class German counselling taxonomy using 5-fold cross-validation, this improves macro-F1 by 9--42% relative depending on encoder and substantially improves dialogue-flow alignment. Cross-dataset validation on HOPE suggests that improvements transfer across languages and counselling domains. In systematic ablations across pretrained encoders and architectures, the findings indicate that transition regularization provides consistent gains and disproportionately benefits weaker baseline models. The results suggest that lightweight discourse-flow priors complement pretrained encoders, especially in fine-grained, data-sparse dialogue tasks.

Problem

• Next Dialogue Act Prediction
• Dialogue Act
• Counselling Conversations
• Data Sparsity
• Dialogue Flow

Innovation

• transition-matrix regularization
• next dialogue act prediction
• KL regularization
• dialogue-flow alignment
• cross-dataset validation