Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale

Computer Science > Computation and Language arXiv:2610.10758 (cs) [Submitted on 7 Oct 2026] Title: Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale Authors: 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)

计算机科学 > 计算与语言 arXiv:2610.10758 (cs) [提交于 2026 年 10 月 7 日] 标题：先澄清，后聚焦：用于大规模对话分析的陈述标准化 作者：Mikhail L. Arbuzov（独立研究员）、Karan Dave（独立研究员）、Evgeniya Dontsova（独立研究员）、Yaodong Hu（独立研究员）、Vincent Lao（独立研究员）、Navita Jain（独立研究员）、Sisong Bei（独立研究员）、Dmitry Dimov（独立研究员）

Abstract: Enterprise conversation analytics asks many questions of millions of interactions. Each question can require reconstructing what people mean and identifying which information matters, repeating costly interpretive work across the same transcripts. We propose a simple principle: clarify the text, then focus the reader. Statement normalization transforms dialogue into short, speaker-attributed statements with source references and semantic tags. The statements make meaning more explicit; the tags support selecting evidence for a particular question.

摘要：企业对话分析需要从数百万次交互中提出许多问题。每个问题都可能需要重构人们的意图并识别哪些信息是重要的，这导致在相同的转录本上重复进行昂贵的解释工作。我们提出了一个简单的原则：先澄清文本，再聚焦读者。陈述标准化将对话转换为带有来源引用和语义标签的简短、归属于发言人的陈述。这些陈述使含义更加明确；标签支持为特定问题选择证据。

Downstream models can use the full representation or a relevant subset, depending on what helps them make the decision. In an offer-suppression task on customer-service calls, normalization improves a supervised classifier without selection, while weaker prompted readers benefit from both normalization and selection. A small model can learn the normalization contract, while lightweight encoders handle tagging and downstream decisions. Sharing this preparation across questions supports an inference pipeline built entirely from small models, making analytics over millions of conversations substantially less expensive.

下游模型可以使用完整表示或相关子集，具体取决于什么有助于它们做出决策。在客户服务电话的优惠抑制任务中，标准化在没有选择的情况下改进了监督分类器，而较弱的提示阅读器则同时受益于标准化和选择。一个小模型可以学习标准化契约，而轻量级编码器则处理标记和下游决策。在不同问题间共享这种准备工作，支持了一个完全由小模型构建的推理流水线，使得对数百万次对话的分析成本大幅降低。