Multilingual Artificial Intelligence

1. Auflage 2025
ISBN: 978-1-032-74722-4
Verlag: Routledge

Buch, Englisch, 178 Seiten, Format (B × H): 174 mm x 246 mm, Gewicht: 332 g

Multilingual Artificial Intelligence is a guide for non-computer science specialists and learners looking to explore the implementation of AI technologies to solve real-life problems involving language data.

Focusing on multilingual, multicultural, pre-trained large language models and their practical use through fine-tuning and prompt engineering, Wang and Smith demonstrate how to apply this new technology in areas such as information retrieval, semantic webs, and retrieval augmented generation, to improve both human productivity and machine intelligence. Finally, they discuss the human impact of language technologies in the cultural context, and provide an AI competence framework for users to design their own learning journey.

This innovative text is essential reading for all students, professionals, and researchers in language, linguistics, and related areas looking to understand how to integrate multilingual and multicultural artificial intelligence technology into their research and practice.

Zielgruppe

Academic, Postgraduate, and Undergraduate Advanced

Autoren/Hrsg.

Wang, Peng

Smith, Pete

Fachgebiete

• Mathematik | Informatik EDV | Informatik Daten / Datenbanken
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Spracherkennung, Sprachverarbeitung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Geisteswissenschaften Sprachwissenschaft Übersetzungswissenschaft, Translatologie, Dolmetschen
• Geisteswissenschaften Sprachwissenschaft Sprachwissenschaften

Inhaltsverzeichnis

List of Figures

List of Tables

Preface

Part One: Fundamentals of multilingual artificial intelligence

Chapter 1: Multilingual AI in a mathematical theory of communication

Chapter 2: Data landscape for multilingual AI

Chapter 3: Basic techniques to achieve artificial intelligence

Chapter 4: Symbolic meaning and vector semantics

Part Two: Large Language models: theories and applications

Chapter 5: Multilingual large language models, fine-tuning, and prompt engineering

Chapter 6: Multilingual and cross-lingual information retrieval

Chapter 7: Augmenting LLM performance with human knowledge

Part Three: Culture and multicultual AI

Chapter 8: Multilingual AI in practice

Chapter 9: Multicultural AI

Chapter 10: Multilingual and multicultural AI—pedagogy, proficiency, policy, and predictions

References

Index

Über Autor(innen)

Peng Wang is an IT analyst and the chair of the Multilingual AI Track. She is the co-author of Machine Learning in Translation.

Pete Smith is Professor of Modern Languages at the University of Texas Arlington, where he also serves as Chief Analytics and Data Officer.