Statistical Machine Translation

This introductory text to statistical machine translation (SMT) provides all of the theories and methods needed to build a statistical machine translator, such as Google, or any other search engine on the web. In general, statistical techniques allow automatic translation systems to be built quickly for any language-pair using only translated texts and generic software. With increasing globalization, statistical machine translation will be central to communication and commerce. Based on courses and tutorials, and classroom-tested globally, it is ideal for instruction or self-study, for advanced undergraduates and graduate students in computer science and/or computational linguistics, and researchers in natural language processing. The companion website provides open-source corpora and tool-kits.

Preface	p. xi
Foundations	p. 1
Introduction	p. 3
Overview	p. 4
History of Machine Translation	p. 14
Applications	p. 20
Available Resources	p. 23
Summary	p. 26
Words, Sentences, Corpora	p. 33
Words	p. 33
Sentences	p. 45
Corpora	p. 53
Summary	p. 57
Probability Theory	p. 63
Estimating Probability Distributions	p. 63
Calculating Probability Distributions	p. 67
Properties of Probability Distributions	p. 71
Summary	p. 75
Core Methods	p. 79
Word-Based Models	p. 81
Machine Translation by Translating Words	p. 81
Learning Lexical Translation Models	p. 87
Ensuring Fluent Output	p. 94
Higher IBM Models	p. 96
Word Alignment	p. 113
Summary	p. 118
Phrase-Based Models	p. 127
Standard Model	p. 127
Learning a Phrase Translation Table	p. 130
Extensions to the Translation Model	p. 136
Extensions to the Reordering Model	p. 142
EM Training of phrase-Based Models	p. 145
Summary	p. 148
Decoding	p. 155
Translation Process	p. 156
Beam Search	p. 158
Future Cost Estimation	p. 167
Other Decoding Algorithms	p. 172
Summary	p. 176
Language Models	p. 181
N-Gram Language Models	p. 182
Count Smoothing	p. 188
Interpolation and Back-off	p. 196
Managing the Size of the Model	p. 204
Summary	p. 212
Evaluation	p. 217
Manual Evaluation	p. 218
Automatic Evaluation	p. 222
Hypothesis Testing	p. 232
Task-Oriented Evaluation	p. 237
Summary	p. 240
Advanced Topics	p. 247
Discriminative Training	p. 249
Finding Candidate Translations	p. 250
Principles of Discriminative Methods	p. 255
Parameter Tuning	p. 263
Large-Scale Discriminative Training	p. 272
Posterior Methods and System Combination	p. 278
Summary	p. 283
Integrating Linguistic Information	p. 289
Transliteration	p. 291
Morphology	p. 296
Syntactic Restructuring	p. 302
Syntactic Features	p. 310
Factored Translation Models	p. 314
Summary	p. 320
Tree-Based Models	p. 331
Synchronous Grammars	p. 331
Learning Synchronous Grammars	p. 337
Decoding by Parsing	p. 346
Summary	p. 363
Bibliography	p. 371
Author Index	p. 416
Index	p. 427
Table of Contents provided by Ingram. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Statistical Machine Translation

Summary

Table of Contents

Supplemental Materials