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

Key points

• We propose a simple principle: clarify the text, then focus the reader.1
• Statement normalization transforms dialogue into short, speaker-attributed statements with source references and semantic tags.1
• 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.1
• Sharing this preparation across questions supports an inference pipeline built entirely from small models, making analytics over millions of conversations substantially less expensive.1

Sources (1)

• [1]Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 06:22 PM

  Enterprise conversation analytics asks many questions of millions of interactions.

  We propose a simple principle: clarify the text, then focus the reader.

Extractive summary: sentences quoted from the sources.