liveBook · Manning

Rule-based conversation manager

As explained in Natural Language Processing in Action, Second Edition

A rule-based conversation manager controls dialogue with explicit rules that determine permitted states, actions, or responses.

A rule-based conversation manager grounds an LLM inside explicit dialogue rules. It can constrain onboarding, permission requests, response length, and safety-sensitive turns instead of trusting generation alone. section 12.5.2

Permission-aware math tutoring

An onboarding flow asks whether the user is a student or parent. It requests explicit parental permission before allowing a child to use the tutor over WhatsApp, then hands the phone to the student only after agreement.

How Natural Language Processing in Action, Second Edition covers it

How deep it goes
Demonstrates rule-writing, conversation memory, and a Python wrapper, while stopping short of a general state-machine implementation.
Examples
Uses a math tutor, parental consent dialogue, WhatsApp onboarding, and number-sequence questions to expose generative unreliability.
What it assumes
Assumes familiarity with LLM prompts and chatbot conversations while demonstrating conversation history and memory configuration.
What you can do after
Operate/configure it through LangChain prompts, conversation memory, repeated response checks, and explicit onboarding constraints.
How it connects
Connects LLMs with chatbots, prompt templates, conversation history, conventional NLP algorithms, and reinforcement learning with human feedback.
Cover of Natural Language Processing in Action, Second Edition
liveBookmanning.com
Read Natural Language Processing in Action, Second Edition on liveBook Get the book at manning.com

This explainer was generated by Manning's knowledge graph from the text of Natural Language Processing in Action, Second Edition. The section links point to the parts of the book it draws on.