Natural Language Generation

2010-06-29

AI Summary

Existing NLG research disproportionately emphasizes short-term LLM advancements, neglecting foundational theory and sustainable industrial deployment. Method: This work systematically constructs a long-term-oriented NLG framework grounded in user needs, rigorous evaluation, safety governance, and real-world deployment—integrating insights from rule-based systems, statistical machine learning, and early neural models, while incorporating human-in-the-loop evaluation, software engineering practices (e.g., testing, maintenance), and decades of evolutionary experience. Contribution/Results: It establishes the first comprehensive, historically grounded NLG knowledge system spanning over thirty years of development. Its core contribution is a principle-driven NLG methodology emphasizing cross-domain applicability and industrial-grade robustness. Complemented by practical case studies, critical reflections, and curated resources, this framework serves as an authoritative reference for researchers, applied developers, and interdisciplinary practitioners—bridging the gap between NLG research and sustainable, production-ready deployment.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Life-Long and Continual Learning
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This book provides a broad overview of Natural Language Generation (NLG), including technology, user requirements, evaluation, and real-world applications. The focus is on concepts and insights which hopefully will remain relevant for many years, not on the latest LLM innovations. It draws on decades of work by the author and others on NLG. The book has the following chapters: Introduction to NLG; Rule-Based NLG; Machine Learning and Neural NLG; Requirements; Evaluation; Safety, Maintenance, and Testing; and Applications. All chapters include examples and anecdotes from the author's personal experiences, and end with a Further Reading section. The book should be especially useful to people working on applied NLG, including NLG researchers, people in other fields who want to use NLG, and commercial developers. It will not however be useful to people who want to understand the latest LLM technology. There is a companion site with more information at https://ehudreiter.com/book/

Problem

• Overview of Natural Language Generation
• Focus on enduring NLG concepts
• Useful for applied NLG professionals

Innovation

• Rule-Based NLG approach
• Machine Learning techniques
• Neural NLG methods