Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914492519022592 |
|---|---|
| author | Rudolph, Eric Steigerwald, Philipp Albrecht, Jens |
| author_facet | Rudolph, Eric Steigerwald, Philipp Albrecht, Jens |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18539 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations Rudolph, Eric Steigerwald, Philipp Albrecht, Jens Computation and Language Artificial Intelligence 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. |
| title | Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.18539 |