arXiv cs.CL· Eric Rudolph, Philipp Steigerwald, Jens Albrecht·· 12 小时前AI 评分20
用转移矩阵正则化改进心理咨询对话中的下一对话行为预测
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
AI 导读
研究提出一种 KL 正则项，将预测的对话行为分布与语料统计的转移模式对齐，用于下一对话行为预测（NDAP）。在 60 类德语心理咨询分类体系上做 5 折交叉验证，macro-F1 相对提升 9–42%（视编码器而定），对话流对齐显著改善；在 HOPE 上的跨数据集验证显示提升可跨语言与咨询领域迁移。系统消融表明该正则化收益稳定，且对较弱基线模型帮助更大。
正文 · 原文
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.
| Comments: | Findings of ACL 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.18539 [cs.CL] |
| (or arXiv:2604.18539v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.18539 arXiv-issued DOI via DataCite |
|
| Journal reference: | Findings of the Association for Computational Linguistics: ACL 2026, pages 25442-25457 |
| Related DOI: | https://doi.org/10.18653/v1/2026.findings-acl.1271
DOI(s) linking to related resources |
Submission history
From: Eric Rudolph [view email]
[v1]
Mon, 20 Apr 2026 17:33:37 UTC (444 KB)
[v2]
Mon, 2 Nov 2026 13:52:42 UTC (411 KB)
来源：arXiv cs.CL · arxiv.org