This book compares and contrasts the principles and practices of rule-based machine translation (RBMT), statistical machine translation (SMT), and example-based machine translation (EBMT). Presenting numerous examples, the text introduces language divergence as the fundamental challenge to machine translation, emphasizes and works out word alignment, explores IBM models of machine translation, covers the mathematics of phrase-based SMT, provides complete walk-throughs of the working of interlingua-based and transfer-based RBMT, and analyzes EBMT, showing how translation parts can be extracted and recombined to automatically translate a new input.
Table of Contents
List of Figures, List of Tables, Preface, Acknowledgments, About the Author, 1. Introduction, 2. Learning Bilingual Word Mappings, 3. IBM Model of Alignment, 4. Phrase-Based Machine Translation, 5. Rule-Based Machine Translation (RBMT), 6. Example-Based Machine Translation, Index
Pushpak Bhattacharyya is Vijay and Sita Vashee chair professor of computer science and engineering at the Indian Institute of Technology (IIT) Bombay, where he has been teaching and researching for the last 25 years. He was educated at IIT Kharagpur (B.Tech), IIT Kanpur (M.Tech), and IIT Bombay (Ph.D). While earning his Ph.D, he was visiting scholar at the Massachusetts Institute of Technology. Subsequently, he has been visiting professor at Stanford University and University of Grenoble, and distinguished lecturer at the University of Houston. Dr. Bhattacharyya's research interests include natural language processing, machine learning, machine translation, information extraction, sentiment analysis, and cross-lingual search, in which he has published extensively. Currently, he is associate editor of ACM Transactions on Asian Language Information Processing and vice president-elect of Association of Computational Linguistics (ACL).