 Название: Natural Language Generation
Автор: Ehud Reiter
Издательство: Springer
Год: 2025
Страниц: 208
Язык: английский
Формат: pdf (true), epub
Размер: 27.3 MB
In late 2022, the prominence of Natural Language Generation (NLG) surged with the advent of advanced language models like ChatGPT. While these developments have captivated both academic and commercial sectors, the focus has predominantly been on the latest innovations, often overlooking the rich history and foundational work in NLG. This book aims to provide a comprehensive overview of NLG, encompassing not only language models but also alternative approaches, user requirements, evaluation methods, safety and testing protocols, and practical applications. Drawing on decades of NLG research, the book is designed to be a valuable resource for both researchers and developers, offering insights that remain relevant far beyond the current technological landscape.
Natural Language Generation focuses on data-to-text but also looks at other types of NLG including text summarization. The book takes a holistic approach to NLG, looking at requirements (what users are looking for), design, data issues, testing, evaluation, safety and ethical issues as well as technology. The holistic approach is unique to this book and is very valuable for people building real-world NLG systems, and for academics and researchers who are interested in applied NLG.
Natural Language Generation systems use Artificial Intelligence (AI) and natural language processing (NLP) techniques within software systems that generate texts in human languages such as English, Chinese, and Arabic. In other words, NLG is the science of AI systems that can write. As such it is related to (but not the same as) Natural Language Understanding (NLU), which is the science of AI systems that can read and extract meanings from human-written texts. Natural Language Generation has recently become more prominent because of the success of ChatGPT and other generative language models, but the field has been around for decades. AI and NLP techniques such as Machine Learning and language models are widely used, but they do not tell the whole story.
Instead of building an NLG system using rules from domain experts, we can use Machine Learning (ML) techniques to create an NLG model. The model is trained on data (e.g. inputs and outputs for NLG) and can apply the behaviour it has learnt from the data to generate new NLG outputs from novel NLG inputs. At the time of writing, most machine learning in NLG uses neural models, that is models that are loosely inspired by how neurons in the human brain work. There are many possibilities within the broad space of using ML and neural techniques in NLG. Perhaps the most fundamental distinction is in how models are trained:
- Trained models
- Fine-tuned models
- Prompted models
Contents:
1. Introduction to NLG
2. Rule-Based NLG
3. Machine Learning and Neural NLG
4. Requirements
5. Evaluation
6. Safety, Testing, and Maintenance
7. Applications
Скачать Natural Language Generation
|
Навигация
Вход на сайт
Реклама
Natural Language Generation 
