Natural language generation:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Cham, Switzerland
Springer
[2025]
|
| Ausgabe: | 2025 |
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | Approx. 250 p. - 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.The author, who previously co-authored a seminal NLG book in 2000, emphasizes high-level concepts and methodologies, ensuring the material's longevity and utility. The book is structured to balance technical depth with practical relevance, including chapters on rule-based and neural NLG approaches, user requirements, rigorous evaluation techniques, and safety considerations. Real-world applications, particularly in journalism, business intelligence, summarization, and medicine, are explored to illustrate NLG's potential and scalability. . - With personal anecdotes and examples from the author's experiences, this book provides a unique and engaging perspective on the evolving field of NLG, making it an indispe |
| Beschreibung: | xiii, 202 Seiten Illustrationen, Diagramme |
| ISBN: | 9783031685811 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV049948567 | ||
| 003 | DE-604 | ||
| 005 | 20241204 | ||
| 007 | t| | ||
| 008 | 241112s2025 xx a||| |||| 00||| eng d | ||
| 020 | |a 9783031685811 |c hbk |9 978-3-031-68581-1 | ||
| 035 | |a (DE-599)BVBBV049948567 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-473 | ||
| 084 | |a ST 306 |0 (DE-625)143654: |2 rvk | ||
| 100 | 1 | |a Reiter, Ehud |d 1960- |e Verfasser |0 (DE-588)140655018 |4 aut | |
| 245 | 1 | 0 | |a Natural language generation |c Ehud Reiter |
| 264 | 1 | |a Cham, Switzerland |b Springer |c [2025] | |
| 264 | 4 | |c © 2025 | |
| 300 | |a xiii, 202 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Approx. 250 p. - 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.The author, who previously co-authored a seminal NLG book in 2000, emphasizes high-level concepts and methodologies, ensuring the material's longevity and utility. The book is structured to balance technical depth with practical relevance, including chapters on rule-based and neural NLG approaches, user requirements, rigorous evaluation techniques, and safety considerations. Real-world applications, particularly in journalism, business intelligence, summarization, and medicine, are explored to illustrate NLG's potential and scalability. . - With personal anecdotes and examples from the author's experiences, this book provides a unique and engaging perspective on the evolving field of NLG, making it an indispe | ||
| 650 | 4 | |a bicssc | |
| 650 | 4 | |a bicssc | |
| 650 | 4 | |a bicssc | |
| 650 | 4 | |a bisacsh | |
| 650 | 4 | |a bisacsh | |
| 650 | 4 | |a bisacsh | |
| 650 | 4 | |a bisacsh | |
| 650 | 4 | |a bisacsh | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Computational linguistics | |
| 650 | 4 | |a Natural language processing (Computer science) | |
| 650 | 4 | |a Artificial intelligence | |
| 653 | |a Hardcover, Softcover / Informatik, EDV/Informatik | ||
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-3-031-68582-8 |
| 856 | 4 | 2 | |m Digitalisierung UB Bamberg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035286634&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-035286634 | |
Datensatz im Suchindex
| _version_ | 1817983086419247104 |
|---|---|
| adam_text |
Contents 1 2 1 2 3 4 5 6 6 Introduction to NLG. 1.1 What Is Natural Language Generation?. 1.2 Example: Weather Forecast (Data-to-Text). 1.2.1 Use Case: Point Weather Forecasts for General Public. 1.2.2 Technology: Rule-Based NLG. 1.2.3 Evaluation. 1.3 Example: Summarising Consultations (Text-to-Text). 1.3.1 Use Case: Generating Summaries of Doctor-Patient Consultations. 1.3.2 Technology. 1.3.3 Evaluation. 1.4 Technologies. 1.4.1 Rule-Based NLG. 1.4.2 Machine Learning and Neural Models. 1.4.3 Combining Rules and ML. 1.5 Effectiveness. 1.5.1 Requirements. 1.5.2
Evaluation. 1.5.3 Safety, Testing, and Maintenance. 1.6 Use Cases and Applications. 1.7 Ethics. 1.8 A Very Short History of NLG. 1.8.1 Early History. 1.8.2 1990-2014 . 1.8.3 2015-2024 . 1.8.4 My Personal NLG Journey. . 1.9 Resources and Further Reading. 6 8 8 9 10 11 12 13 13 14 15 16 18 19 19 20 20 22 22 Rule-Based NLG. 2.1 NLG Pipeline. 2.2 Examples. 25 26 27 ix
Contents X 2.2.1 DrivingFeedback. 2.2.2 Babytalk. Signal Analysis. 2.3.1 Noise Detection: Principles. 2.3.2 Pattern Detection: Principles. 2.3.3 Techniques for Signal Analysis. Data Interpretation. 2.4.1 Principles. 2.4.2 Techniques. Document Planning. 2.5.1 Principles. 2.5.2 Techniques. Microplanning. 2.6.1 Lexical Choice. 2.6.2 Generating Referring Expressions. 2.6.3 Aggregation. Surface
Realisation. 2.7.1 Principles. 2.7.2 Techniques. Template NLG . 2.8.1 Principles. 2.8.2 Techniques. Further Reading and Resources. 28 29 30 31 31 33 33 33 34 35 35 36 37 37 39 40 41 41 42 43 44 45 46 Machine Learning and Neural NLG. 3.1 Examples. 3.1.1 Very Simple Trained Model: a vs. an. 3.1.2 Fine-Tuned Neural Model: Facebook Weather Dialogues. 3.1.3 Prompted Model: Using ChatGPT to Generate Weather Forecasts. 53 3.2 Machine Learning Models for NLG. 3.2.1 Classifiers. 3.2.2 N-Gram Language Models. 3.2.3 Early Neural Models. 3.2.4
Transformers and Foundation Models. 3.2.5 Instruction Tuning and RLHF. 3.2.6 End-to-end vs. Modular Architectures. 3.3 Training Data. 3.3.1 DataSources. 3.3.2 Data Set Criteria. 3.3.3 Impact of Training Data on Prompted Models. 3.3.4 Synthetic Data and Data Augmentation. 3.3.5 Including Examples in Prompts. 3.4 Issues. 3.4.1 Domain Shift. 49 50 50 52 2.3 2.4 2.5 2.6 2.7 2.8 2.9 3 55 55 56 57 57 58 60 60 61 62 63 64 65 65 66
Contents xi 3.4.2 Question Answering. 3.4.3 Auditability and Controllability. 3.4.4 Legal and Regulatory Issues . 3.5 Further Reading and Resources. 67 68 68 69 4 Requirements. 4.1 Quality Criteria: Texts. 4.1.1 Readability and Fluency. 4.1.2 Accuracy. 4.1.3 Content. 4.1.4 Utility. 4.2 Quality Criteria: Systems. 4.2.1 Non-functional Requirements. 4.2.2 Consistency and Variation. 4.2.3 Average vs. Worst Case. 4.3 Workflow. 4.3.1 Fully Automatic NLG. 4.3.2 Human Checking and
Editing. 4.3.3 Creating Drafts for Human Writers. 4.4 Text and Graphics. 4.4.1 Decision Support. 4.4.2 Other Use Cases. 4.4.3 Combining Text and Graphics. 4.5 Requirements Acquisition. 4.5.1 User Studies. 4.5.2 Manual Corpus Analysis. 4.5.3 Stakeholders. 4.6 Further Reading. 71 72 73 74 76 76 77 77 78 79 80 80 80 81 82 83 84 84 85 85 88 91 92 5 Evaluation . 5.1 Example: Smoking Cessation (Impact Evaluation) . 5.2 Fundamentals. 5.2.1 Stakeholder Perspective. 5.2.2 Hypothesis Testing. 5.2.3 Statistical Hypothesis
Testing. 5.2.4 Experimental Design, Execution, Reporting, and Follow-Up. 99 5.2.5 Research Questions. 5.2.6 Replication. 5.2.7 Ecological Validity: Artificial Versus Real-World Context. 5.2.8 Test Data: Representative, Different from Training Data. 5.3 Human Evaluation. 5.3.1 Туpes of Human Evaluation. 5.3.2 Experimental Design. 5.3.3 Issues in Human Evaluation. 5.4 Automatic Evaluation. 93 94 96 96 97 98 101 101 103 104 105 105 110 118 121
xii Contents 5.5 5.6 5.7 5.8 5.4.1 Types of Automatic Evaluation. 5.4.2 Experimental Design . 5.4.3 Examples of Metrics. 5.4.4 Validation of Metrics. Impact Evaluation. 5.5.1 Comparison Between Users: Randomised Controlled Trials and A/В Testing. 5.5.2 Historical Comparison. 5.5.3 Challenges. Commercial Evaluation. 5.6.1 Costs. 5.6.2 Benefits. 5.6.3 Risks. 5.6.4 Return on Investment (ROI). Ten Tips on Evaluating NLG. Further Reading. 6 Safety, Testing, and Maintenance. 6.1
Safety. 6.1.1 Safety Concerns in NLG. 6.1.2 Approaches to Addressing Safety Concerns. 6.2 Software Testing of NLG Systems. 6.2.1 Testing Systems with Variable Outputs. 6.3 Maintenance. 6.3.1 Changes in Domain and User Needs. 6.3.2 New Users and Use Cases. 6.3.3 Changes in Models . 6.4 Further Reading and Resources. 7 Applications . 7.1 7.2 7.3 7.4 7.5 Key Attributes of Successful NLG Applications. 7.1.1 Volume and Scalability. 7.1.2 Data Availability. 7.1.3 Accuracy. 7.1.4 Maintainability and Adaptability . 7.1.5 Acceptability and Trust. 7.1.6 Conforming to Genre and
Sublanguage. Journalism. 7.2.1 Example: BBC Election Reporter. 7.2.2 Types ofNews. 7.2.3 Fake News. Business Intelligence. 7.3.1 Example: Covid Reporter. Summarisation. 7.4.1 Example: Summarising Emails with Google Bard. Medical Applications. 122 124 128 130 134 134 134 135 136 136 137 137 138 139 140 143 143 144 148 151 152 152 154 155 156 157 159 159 159 160 161 161 163 164 164 165 166 168 169 169 170 171 172
xiii Contents 7.6 7.5.1 Use Case: Reporting. 173 7.5.2 Use Case: Patient Information and Behaviour Change. 175 7.5.3 Use Case: Clinical Decision Support. 176 7.5.4 Medical Business Intelligence Use Cases. 177 7.5.5 Safety. 178 Further Reading. 179 References. 181 Index. 197 |
| any_adam_object | 1 |
| author | Reiter, Ehud 1960- |
| author_GND | (DE-588)140655018 |
| author_facet | Reiter, Ehud 1960- |
| author_role | aut |
| author_sort | Reiter, Ehud 1960- |
| author_variant | e r er |
| building | Verbundindex |
| bvnumber | BV049948567 |
| classification_rvk | ST 306 |
| ctrlnum | (DE-599)BVBBV049948567 |
| discipline | Informatik |
| edition | 2025 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV049948567</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20241204</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">241112s2025 xx a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9783031685811</subfield><subfield code="c">hbk</subfield><subfield code="9">978-3-031-68581-1</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV049948567</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-473</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 306</subfield><subfield code="0">(DE-625)143654:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Reiter, Ehud</subfield><subfield code="d">1960-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)140655018</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Natural language generation</subfield><subfield code="c">Ehud Reiter</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cham, Switzerland</subfield><subfield code="b">Springer</subfield><subfield code="c">[2025]</subfield></datafield><datafield tag="264" ind1=" " ind2="4"><subfield code="c">© 2025</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xiii, 202 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Approx. 250 p. - 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.The author, who previously co-authored a seminal NLG book in 2000, emphasizes high-level concepts and methodologies, ensuring the material's longevity and utility. The book is structured to balance technical depth with practical relevance, including chapters on rule-based and neural NLG approaches, user requirements, rigorous evaluation techniques, and safety considerations. Real-world applications, particularly in journalism, business intelligence, summarization, and medicine, are explored to illustrate NLG's potential and scalability. . - With personal anecdotes and examples from the author's experiences, this book provides a unique and engaging perspective on the evolving field of NLG, making it an indispe</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bicssc</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Computational linguistics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Natural language processing (Computer science)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">Hardcover, Softcover / Informatik, EDV/Informatik</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-3-031-68582-8</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Bamberg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035286634&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-035286634</subfield></datafield></record></collection> |
| id | DE-604.BV049948567 |
| illustrated | Illustrated |
| indexdate | 2024-12-09T17:02:56Z |
| institution | BVB |
| isbn | 9783031685811 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-035286634 |
| open_access_boolean | |
| owner | DE-473 DE-BY-UBG |
| owner_facet | DE-473 DE-BY-UBG |
| physical | xiii, 202 Seiten Illustrationen, Diagramme |
| publishDate | 2025 |
| publishDateSearch | 2024 |
| publishDateSort | 2024 |
| publisher | Springer |
| record_format | marc |
| spelling | Reiter, Ehud 1960- Verfasser (DE-588)140655018 aut Natural language generation Ehud Reiter Cham, Switzerland Springer [2025] © 2025 xiii, 202 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Approx. 250 p. - 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.The author, who previously co-authored a seminal NLG book in 2000, emphasizes high-level concepts and methodologies, ensuring the material's longevity and utility. The book is structured to balance technical depth with practical relevance, including chapters on rule-based and neural NLG approaches, user requirements, rigorous evaluation techniques, and safety considerations. Real-world applications, particularly in journalism, business intelligence, summarization, and medicine, are explored to illustrate NLG's potential and scalability. . - With personal anecdotes and examples from the author's experiences, this book provides a unique and engaging perspective on the evolving field of NLG, making it an indispe bicssc bisacsh Machine learning Computational linguistics Natural language processing (Computer science) Artificial intelligence Hardcover, Softcover / Informatik, EDV/Informatik Erscheint auch als Online-Ausgabe 978-3-031-68582-8 Digitalisierung UB Bamberg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035286634&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Reiter, Ehud 1960- Natural language generation bicssc bisacsh Machine learning Computational linguistics Natural language processing (Computer science) Artificial intelligence |
| title | Natural language generation |
| title_auth | Natural language generation |
| title_exact_search | Natural language generation |
| title_full | Natural language generation Ehud Reiter |
| title_fullStr | Natural language generation Ehud Reiter |
| title_full_unstemmed | Natural language generation Ehud Reiter |
| title_short | Natural language generation |
| title_sort | natural language generation |
| topic | bicssc bisacsh Machine learning Computational linguistics Natural language processing (Computer science) Artificial intelligence |
| topic_facet | bicssc bisacsh Machine learning Computational linguistics Natural language processing (Computer science) Artificial intelligence |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=035286634&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT reiterehud naturallanguagegeneration |