对话动作预测中的转移矩阵正则化：在咨询对话中的应用
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
AI总结：
本文通过KL正则化使对话动作预测与转移模式对齐，在德国咨询分类中提升宏F1分数9-42%，并验证其跨语言和领域泛化能力，尤其在数据稀少任务中表现突出。
摘要：
本文研究如何将经验对话流程统计纳入下一步对话动作预测。提出KL正则化项，使预测动作分布与语料库中的转移模式对齐。在60类德国咨询分类上，通过五折交叉验证，该方法在不同编码器下提升宏F1分数9-42%，并显著改善对话流程对齐。在HOPE数据集上的跨数据集验证表明，改进可跨语言和咨询领域转移。系统消融实验显示，转移正则化提供一致收益，并显著帮助弱基线模型。结果表明，轻量级话语流程先验可补充预训练编码器，尤其在细粒度、数据稀少的对话任务中。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
