"The field of machine translation has recently been energized by the emergence of statistical techniques, which have brought the dream of automatic language translation closer to reality. This class-tested textbook, authored by an active researcher...
mehr
Universitätsbibliothek der Eberhard Karls Universität
Fernleihe:
keine Fernleihe
"The field of machine translation has recently been energized by the emergence of statistical techniques, which have brought the dream of automatic language translation closer to reality. This class-tested textbook, authored by an active researcher in the field, provides a gentle and accessible introduction to the latest methods and enables the reader to build machine translation systems for any language pair." "It provides the necessary grounding in linguistics and probabilities, and covers the major models for machine translation: word-based, phrase-based, and tree-based, as well as machine translation evaluation, language modeling, discriminative training, and advanced methods to integrate linguistic annotation. The book reports on the latest research and outstanding challenges, and enables novices as well as experienced researchers to make contributions to the field. It is ideal for students at undergraduate and graduate level, or for any reader interested in the latest developments in machine translation."--Jacket Cover -- Half-title -- Title -- Copyright -- Dedication -- Contents -- Preface -- Part I Foundations -- Chapter 1 Introduction -- 1.1 Overview -- 1.2 History of Machine Translation -- 1.3 Applications -- 1.4 Available Resources -- 1.5 Summary -- Chapter 2 Words, Sentences, Corpora -- 2.1 Words -- 2.2 Sentences -- 2.3 Corpora -- 2.4 Summary -- Chapter 3 Probability Theory -- 3.1 Estimating Probability Distributions -- 3.2 Calculating Probability Distributions -- 3.3 Properties of Probability Distributions -- 3.4 Summary -- Part II Core Methods -- Chapter 4 Word-Based Models -- 4.1 Machine Translation by Translating Words -- 4.2 Learning Lexical Translation Models -- 4.3 Ensuring Fluent Output -- 4.4 Higher IBM Models -- 4.5 Word Alignment -- 4.6 Summary -- Chapter 5 Phrase-Based Models -- 5.1 Standard Model -- 5.2 Learning a Phrase Translation Table -- 5.3 Extensions to the Translation Model -- 5.4 Extensions to the Reordering Model -- 5.5 EM Training of Phrase-Based Models -- 5.6 Summary -- Chapter 6 Decoding -- 6.1 Translation Process -- 6.2 Beam Search -- 6.3 Future Cost Estimation -- 6.4 Other Decoding Algorithms -- 6.5 Summary -- Chapter 7 Language Models -- 7.1 N-Gram Language Models -- 7.2 Count Smoothing -- 7.3 Interpolation and Back-off -- 7.4 Managing the Size of the Model -- 7.5 Summary -- Chapter 8 Evaluation -- 8.1 Manual Evaluation -- 8.2 Automatic Evaluation -- 8.3 Hypothesis Testing -- 8.4 Task-Oriented Evaluation -- 8.5 Summary -- Part III Advanced Topics -- Chapter 9 Discriminative Training -- 9.1 Finding Candidate Translations -- 9.2 Principles of Discriminative Methods -- 9.3 Parameter Tuning -- 9.4 Large-Scale Discriminative Training -- 9.5 Posterior Methods and System Combination -- 9.6 Summary -- Chapter 10 Integrating Linguistic Information -- 10.1 Transliteration -- 10.2 Morphology -- 10.3 Syntactic Restructuring -- 10.4 Syntactic Features -- 10.5 Factored Translation Models -- 10.6 Summary -- Chapter 11 Tree-Based Models -- 11.1 Synchronous Grammars -- 11.2 Learning Synchronous Grammars -- 11.3 Decoding by Parsing -- 11.4 Summary -- Bibliography -- Author Index -- Index.