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

TL;DR

This paper introduces a KL regularization method that incorporates dialogue-flow statistics into Next Dialogue Act Prediction, significantly improving performance and alignment across languages and models.

Contribution

It proposes a novel transition-matrix regularization technique that enhances dialogue act prediction by leveraging corpus-derived transition patterns.

Findings

Improves macro-F1 by 9-42% depending on encoder.

Enhances dialogue-flow alignment in predictions.

Provides consistent gains across models and datasets.

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.