arXiv · Computation and Language· Mikhail L. Arbuzov (Independent researcher), Karan Dave (Independent researcher), Evgeniya Dontsova (Independent researcher), Yaodong Hu (Independent researcher), Vincent Lao (Independent researcher), Navita Jain (Independent researcher), Sisong Bei (Independent researcher), Dmitry Dimov (Independent researcher)·· 3 小时前AI 评分34
Clarify, Then Focus：面向大规模对话分析的语句规范化方法
Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale
AI 导读
论文提出语句规范化（statement normalization）方法，把对话转换为带说话人归属、来源引用和语义标签的短语句，先澄清语义再按问题选取证据。在客服电话的 offer-suppression 任务中，规范化提升了无筛选监督分类器效果，较弱的提示式读者同时受益于规范化与筛选。
来源：arXiv · Computation and Language · arxiv.org