Syntax-based Statistical Machine Translation

This unique book provides a comprehensive introduction to the most popular syntax-based statistical machine translation models, filling a gap in the current literature for researchers and developers in human language technologies. While phrase-based models have previously dominated the field, syntax-based approaches have proved a popular alternative, as they elegantly solve many of the shortcomings of phrase-based models. The heart of this book is a detailed introduction to decoding for syntax-based models.

The book begins with an overview of synchronous-context free grammar (SCFG) and synchronous tree-substitution grammar (STSG) along with their associated statistical models. It also describes how three popular instantiations (Hiero, SAMT, and GHKM) are learned from parallel corpora. It introduces and details hypergraphs and associated general algorithms, as well as algorithms for decoding with both tree and string input. Special attention is given to efficiency, including search approximations such as beam search and cube pruning, data structures, and parsing algorithms. The book consistently highlights the strengths (and limitations) of syntax-based approaches, including their ability to generalize phrase-based translation units, their modeling of specific linguistic phenomena, and their function of structuring the search space.

Table of Contents

Preface
Acknowledgments
Models
Learning from Parallel Text
Decoding I: Preliminaries
Decoding II: Tree Decoding
Decoding III: String Decoding
Selected Topics
Closing Remarks
Bibliography
Authors' Biographies
Author Index
Index

About the Author(s)

Philip Williams, University of Edinburgh
Philip Williams is a Research Associate at the University of Edinburgh, where he completed his Ph.D. in 2014. His main research interest is the integration of linguistic information into statistical machine translation. In his thesis, he applied unification-based constraints to syntax-based statistical machine translation. He is the main contributor to the syntax-based models in the Moses toolkit.

Rico Sennrich, University of Edinburgh
Rico Sennrich is a Research Associate at the University of Edinburgh. He received his Ph.D. in Computational Linguistics from the University of Zurich in 2013. His research focuses on data-driven natural language processing, in particular machine translation, syntax, and morphology. His contributions to syntax-based machine translation include a more efficient algorithm for SCFG decoding, and novel models for syntactic language modelling and productive generation of compounds. He developed syntax-based SMT systems for English-German that were tied for first place in the shared translation tasks of WMT 2014 and 2015.

Matt Post, Johns Hopkins University
Matt Post is a Senior Research Scientist at the Human Language Technology Center of Excellence at Johns Hopkins University, where he has been since completing his Ph.D. at the University of Rochester in 2011. Since 2012, he has co-organized the WMT Conference on Statistical Machine Translation. He is the maintainer of the Apache Joshua statistical machine translation toolkit.

Philipp Koehn, Johns Hopkins University
Philipp Koehn is a Professor of Computer Science at Johns Hopkins University, where he is affiliated with the Center for Language and Speech Processing. He also is the Chair of Machine Translation at the University of Edinburgh. He received his Ph.D. in 2003 from the University of Southern California. He is the creator and maintainer of Moses, the de facto statistical machine translation system, used throughout the world in both research and industry. He is a co-founder of the WMT Conference on Statistical Machine Translation, and author of the 2009 textbook Statistical Machine Translation.

Reviews

I found this book to be a useful reference book for those interested in syntax-based SMT. The book is well organized, which makes it easy for readers to refer to specific aspects of syntax-based SMT. An improvement can be made to the presentation of ideas in this book. Throughout the book, there are many technical keywords, resulting from the complexity of syntax-based SMT. It would be useful to highlight these keywords in a side bar to remind readers that they are important keywords. In addition, although examples are given throughout the book, it would be even more useful to use these examples to illustrate how the algorithms work, so that readers can gain a better understanding of the algorithms.
Christian Hadiwinoto, National University of Singapore - Computational Linguistics, Volume 43, Number 4

Write a Review