用对话流转统计约束模型，提升心理咨询中下一步对话行为预测准确率。
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
- 引入KL正则化项，让模型预测符合真实对话流转模式。
- 在德语心理咨询数据上，宏F1提升9%至42%，对话流对齐显著改善。
- 对弱基线模型增益更大，适合小样本细粒度对话任务使用。
本文研究如何将实际对话流统计数据融入下一步对话行为预测（NDAP）。提出一种KL正则化项，使模型预测的对话行为分布与语料库导出的转移模式对齐。在基于60类德语心理咨询分类体系的数据集上进行5折交叉验证，该方法相对基线模型提升了9%至42%的宏F1，显著改善了对话流一致性。跨数据集验证在HOPE数据集上表明，性能提升可跨语言和咨询领域迁移。系统性消融实验显示，过渡正则化在不同预训练编码器与架构下均带来稳定增益，尤其对表现较弱的模型效果更显著。结果表明，轻量级话语流先验能有效补充预训练编码器，特别适用于细粒度、数据稀疏的对话任务。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。