A Course in Natural Language Processing

ISBN-13: 9783031272257 / Angielski / Twarda / 2024

Yannis Haralambous

Opis

Natural Language Processing is the branch of Artificial Intelligence involving language, be it in spoken or written modality. Teaching Natural Language Processing is difficult due to its inherent connections with other disciplines, such as Linguistics, Cognitive Science, Knowledge Representation, Machine Learning, Data Science, and its latest avatar: Deep Learning. Most introductory NLP books favor one of these disciplines at the expense of others. This book aims to consider three points of view corresponding to three different disciplines, while granting equal importance to each of them. 

Based on a course on Natural Language Processing taught by the author at IMT Atlantique (a grande école d'ingénieurs based in Brest, France) for more than a decade, this book provides a thorough introduction into the topic, based on three threads: the fundamental notions of Linguistics, symbolic Artificial Intelligence methods (based on knowledge representation languages) and statistical methods (involving both legacy machine learning and deep learning tools). Complementary to this introductory text is teaching material such as exercises with solutions, labs with programming code (in Python), exams (with answers and discussion of specific difficulties) and general questions assigned to students as homework, including answers, discussion, and links to related general audience books or scientific publications. 

This material can serve for classes given to undergraduate students, or for professionals in computer science or linguistics wanting to acquire knowledge in the field. As everything is explained, the book is suitable, and warmly recommended, for self-study.

Spis treści

Preface.- 1. Introduction.- Part I. Linguistics.- 2. Phonetics/Phonology.- 3. Graphetics/Graphemics.- 4. Morphemes, Words, Terms.- 5. Syntax.- 6. Semantics (and Pragmatics).- 7. Controlled Natural Languages.- Part II. Mathematical Tools.- 8. Graphs.- 9. Formal Languages.- 10. Logic.- 11.- Ontologies and Conceptual Graphs.- Part III. Data Formats.- 12. Unicode.- 13. XML, TEI, CDL.- Part IV. Statistical Methods.- 14. Counting Words.- 15. Going Neural.- 16. Hints and Expected Results for Exercises.- Acronyms.- Index.

O autorze

Born in Athens, Greece, Yannis Haralambous studied Mathematics in Lille, France, where he obtained a Ph.D. in Algebraic Topology in 1990. Having meanwhile become a TeX aficionado, he then specialized in Digital Typography and founded the typesetting company Atelier Fluxus Virus, which is specialized in scientific and scholarly documents. In 2001, he became a Full Professor at the Computer Science Department of IMT Atlantique in Brest, France, and his research activities migrated to the disciplines of Text Mining, Controlled Natural Languages, Knowledge Representation, and Grapholinguistics. He has published more than 120 research or scientific popularization papers and a book on Fonts and Encodings (O'Reilly, 2004), has supervised 10 PhDs, teaches courses on NLP, Graph Theory and Logic, and is the organizer of the biennial conference “Grapholinguistics in the 21st Century”.

Blurb

Natural Language Processing is the branch of Artificial Intelligence involving language, be it in spoken or written modality. Teaching Natural Language Processing (NLP) is difficult because of its inherent connections with other disciplines, such as Linguistics, Cognitive Science, Knowledge Representation, Machine Learning, Data Science, and its latest avatar: Deep Learning. Most introductory NLP books favor one of these disciplines at the expense of others. 

Based on a course on Natural Language Processing taught by the author at IMT Atlantique for over a decade, this textbook considers three points of view corresponding to three different disciplines, while granting equal importance to each of them. As such, the book provides a thorough introduction to the topic following three main threads: the fundamental notions of Linguistics, symbolic Artificial Intelligence methods (based on knowledge representation languages), and statistical methods (involving both legacy machine learning and deep learning tools). 

Complementary to this introductory text is teaching material, such as exercises and labs with hints and expected results. Complete solutions with Python code are provided for educators on the SpringerLink webpage of the book. This material can serve for classes given to undergraduate and graduate students, or for researchers, instructors, and professionals in computer science or linguistics who wish to acquire or improve their knowledge in the field. The book is suitable and warmly recommended for self-study. 

With a PhD in Algebraic Topology (Lille, 1990), Yannis Haralambous is a TeX aficionado and Full Professor at IMT Atlantique in Brest, France. His research interests cover Text Mining, Controlled Natural Languages, Knowledge Representation, and Grapholinguistics, topics in which he has published over 120 research or scientific popularization papers and a book on Fonts and Encodings (O’Reilly, 2007). He is in charge of IMT Atlantique’s “Data Science” Master track program, where he has been teaching the course that inspired this book.