Description :
The Internet gives us access to a wealth of information in languages we don’t understand. The investigation of automated or semi-automated approaches to translation has become a thriving research field with enormous commercial potential. This volume investigates how machine learning techniques can improve statistical machine translation, currently at the forefront of research in the field.
The book looks first at enabling technologies—technologies that solve problems that are not machine translation proper but are linked closely to the development of a machine translation system. The book then presents new or improved statistical machine translation techniques.
Content :
Series Foreword. Preface. A Statistical Machine Translation Primer. I: Enabling Technologies—Mining Patents for Parallel Corpora. Automatic Construction of Multilingual Name Dictionaries. Named Entity Transliteration and Discovery in Multilingual Corpora. Combination of Statistical Word Alignments Based on Multiple Preprocessing Schemes. Linguistically Enriched Word-Sequence Kernels for Discriminative Language Modeling. II: Machine Translation—Toward Purely Discriminative Training for Tree-Structured Translation Models. Reranking for Large-Scale Statistical Machine Translation. Kernel-Based Machine Translation. Statistical Machine Translation through Global Lexical Selection. Discriminative Phrase Selection for SMT. Semisupervised Learning for Machine Translation. Learning to Combine Machine Translation Systems. References. Contributors. Index. Related Books : | |
 | | MICROSOFT SHAREPOINT 2013 ADMINISTRATION INSIDE OUT
By WILLIAMS, RANDY, CALLAHAN, CA , GIVENS, CHRIS, GROSS, JOHN MILAN, ALDERMAN, BRIAN, BARRERA, JAVIER | |
| |
|
| | |
| | |
No other Books by the same author | |
AARON CHATTERJI
