Syntax-based Statistical Machine Translation (Synthesis Lectures on Human Language Technologies)

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, includingsearch 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.

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. 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.