找回密码
 To register

QQ登录

只需一步,快速开始

扫一扫,访问微社区

Titlebook: Natural Language Generation; Ehud Reiter Textbook 2025 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springe

[复制链接]
楼主: brachytherapy
发表于 2025-3-23 13:32:24 | 显示全部楼层
发表于 2025-3-23 17:02:28 | 显示全部楼层
发表于 2025-3-23 18:11:41 | 显示全部楼层
Rule-Based NLG,generated texts. Rule-based NLG has been overshadowed by neural NLG in recent years, but it is still the best way to build some NLG applications. Rule-based NLG also shows the types of decisions which need to be made in text generation. A good understanding of this helps anyone working in NLG, even if they use other approaches.
发表于 2025-3-24 01:22:06 | 显示全部楼层
Requirements,looks at some of the different quality criteria that people may care about, workflows for using NLG (including human-in-the-loop), textual vs. graphical presentation of information, and methodologies for understanding (acquiring) requirements.
发表于 2025-3-24 03:19:46 | 显示全部楼层
Evaluation,that are rigorous and replicable. This chapter discusses basic evaluation concepts and then describes techniques for human and automatic (metric) evaluation. It also looks at evaluating real-world impact of NLG systems and commercial evaluation.
发表于 2025-3-24 09:19:55 | 显示全部楼层
Applications,cusses some fundamental issues (such as scalability) and then looks in more detail at four areas which NLG has been used commercially for many years: journalism, business intelligence, summarisation, and medicine. Lessons from these long-standing NLG use cases can be applied to newer applications of NLG.
发表于 2025-3-24 14:16:19 | 显示全部楼层
发表于 2025-3-24 17:48:49 | 显示全部楼层
发表于 2025-3-24 19:42:04 | 显示全部楼层
Machine Learning and Neural NLG,This chapter gives an overview of machine learning and neural approaches to NLG, including language models. Because this area is changing very rapidly, the focus is on giving a high-level overview of basic concepts behind models and then discussing data and other issues which are important regardless of the model used.
发表于 2025-3-24 23:09:33 | 显示全部楼层
Textbook 2025pments 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 alternat
 关于派博传思  派博传思旗下网站  友情链接
派博传思介绍 公司地理位置 论文服务流程 影响因子官网 吾爱论文网 大讲堂 北京大学 Oxford Uni. Harvard Uni.
发展历史沿革 期刊点评 投稿经验总结 SCIENCEGARD IMPACTFACTOR 派博系数 清华大学 Yale Uni. Stanford Uni.
QQ|Archiver|手机版|小黑屋| 派博传思国际 ( 京公网安备110108008328) GMT+8, 2025-8-22 05:51
Copyright © 2001-2015 派博传思   京公网安备110108008328 版权所有 All rights reserved
快速回复 返回顶部 返回列表