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.

"The goal of machine translation is to develop algorithms that produce human-quality translations of natural language sentences. The evaluation of machine translation quality is split broadly into two aspects: adequacy and fluency. Adequacy measures how faithfully the meaning of the original sentence is preserved, whereas fluency measures whether this meaning is expressed in valid sentences in the target language. While both of these criteria are difficult to meet, fluency is a much more difficult goal. Generally, this likely has something to do with the asymmetrical nature of producing and understanding sentences; although humans are quite robust at inferring the meaning of text even in the presence of lots of noise and error, the rules that govern grammatical utterances are exacting, subtle, and elusive. To produce understandable text, we can rely on this robust processing hardware, but to produce grammatical text, we have to understand how it works. This dissertation attempts to improve the fluency of machine translation output by explicitly incorporating models of the target language structure into machine translation systems. It is organized into three parts. First, we propose a framework for decoding that decouples the structures of the sentences of the source and target languages, and evaluate it with existing grammatical models as language models for machine translation. Next, we apply lessons from that task to the learning of grammars more suitable to the demands of the machine translation. We then incorporate these grammars, called Tree Substitution Grammars, into our decoding framework.--Leaf vi

This book provides a wide variety of algorithms and models to integrate linguistic knowledge into Statistical Machine Translation (SMT). It helps advance conventional SMT to linguistically motivated SMT by enhancing the following three essential components: translation, reordering and bracketing models. It also serves the purpose of promoting the in-depth study of the impacts of linguistic knowledge on machine translation. Finally it provides a systematic introduction of Bracketing Transduction Grammar (BTG) based SMT, one of the state-of-the-art SMT formalisms, as well as a case study of linguistically motivated SMT on a BTG-based platform.

The dream of automatic language translation is now closer thanks to recent advances in the techniques that underpin statistical machine translation. This class-tested textbook from an active researcher in the field, provides a clear and careful introduction to the latest methods and explains how to build machine translation systems for any two languages. It introduces the subject's building blocks from linguistics and probability, then 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 also reports the latest research, presents the major outstanding challenges, and enables novices as well as experienced researchers to make novel contributions to this exciting area. Ideal for students at undergraduate and graduate level, or for anyone interested in the latest developments in machine translation.

Learn how to build machine translation systems with deep learning from the ground up, from basic concepts to cutting-edge research.

Hierarchical phrase-based translation (Hiero) is a statistical machine translation (SMT) model that encodes translation as a synchronous context-free grammar derivation between source and target language strings (Chiang, 2005; Chiang, 2007). Hiero models are more powerful than phrase-based models in capturing complex source-target reordering as well as discontiguous phrases, while being easier to estimate and decode with compared to their full syntax-based counterparts. In this thesis, we propose improvements to two broad aspects of the Hiero translation pipeline: i) learning Hiero translation model and estimating their parameters and ii) parameter tuning for discriminative log-linear models that are used to decode with such features. We use our own open-source implementation of Hiero called Kriya (Sankaran et al., 2012b) for all the experiments in this thesis. This thesis contains the following specific contributions: We propose a Bayesian model for learning Hiero grammars as an alternative to the heuristic method usually used in Hiero. Our model learns a peaked distribution of grammars, which consistently performs better than the heuristically extracted grammars across several language pairs (Sankaran et al., 2013a). We propose a novel unified-cascade framework for jointly learning alignments and the Hiero translation rules by removing the disconnect between the alignments and extracted synchronous context-free grammar. This is the first time a joint training framework is being proposed for Hiero, where we iterate the two step inference so that it learns in alternate iterations the phrase alignments and then the Hiero rules that are consistent with alignments. We extend our Bayesian model for extracting compact Hiero translation rules using arity-1 grammars, resulting in up to 57% reduction in model size while retaining the translation performance (Sankaran et al., 2011; Sankaran et al., 2012a). We propose several novel approaches for parameter tuning of discriminative log-linear models for SMT which can be used for jointly optimizing towards multiple evaluation metrics. We show that our methods for multi-objective tuning for SMT yield substantial gains in translation quality measured through automatic as well as human evaluations (Sankaran et al., 2013b; Duh et al., 2013).

Statistical Word Alignments represent lexical word-to- word translations between source and target language sentences. They are considered the starting point for many state of the art Statistical Machine Translation (SMT) systems. In this dissertation, we perform an in-depth study of the impact of word alignments at different stages of the phrase-based statistical machine translation pipeline, namely word alignment, phrase extraction, phrase scoring and decoding. Moreover, we establish a multivariate prediction model for different variables of the translation model and overall translation quality using word alignment structure. Based on those models, we identify the most important alignment variables and propose two alternatives to provide more control over alignment structure and thus improve SMT. Our results show that using alignment structure into decoding, via alignment gap features yields significant improvements, specially in situations where translation data is limited.

The Handbook of Natural Language Processing, Second Edition presents practical tools and techniques for implementing natural language processing in computer systems. Along with removing outdated material, this edition updates every chapter and expands the content to include emerging areas, such as sentiment analysis.New to the Second EditionGreater