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

ACL ARR 2026 January Submission5173 Authors

Keywords: Next Dialogue Act Prediction, Dialogue Act Modeling, Regularization, Dialogue Flow Modeling, Structured Prediction

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.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: conversational modeling, task-oriented

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Data resources

Languages Studied: German, English

Submission Number: 5173