Download or read book Generative Training and Smoothing of Hierarchical Phrase Based Translation Models written by Stephan Peitz and published by . This book was released on 2017 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Phrase Based Statistical Machine Translation written by Richard Zens and published by . This book was released on 2008 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Statistical Models for Hierarchical Phrase based Machine Translation written by Matthias Huck and published by . This book was released on 2018 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Improvements in Hierarchical Phrase based Statistical Machine Translation written by Baskaran Sankaran and published by . This book was released on 2013 with total page 133 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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).
Download or read book Syntax based Statistical Machine Translation written by Philip Williams and published by Springer Nature. This book was released on 2022-05-31 with total page 190 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Download or read book Left to Right Hierarchical Phrase based Machine Translation written by Maryam Siahbani and published by . This book was released on 2016 with total page 82 pages. Available in PDF, EPUB and Kindle. Book excerpt: Hierarchical phrase-based translation (Hiero for short) models statistical machine translation (SMT) using a lexicalized synchronous context-free grammar (SCFG) extracted from word aligned bitexts. The standard decoding algorithm for Hiero uses a CKY-style dynamic programming algorithm with time complexity O(n̂3) for source input with n words. Scoring target language strings using a language model in CKY-style decoding requires two histories per hypothesis making it significantly slower than phrase-based translation which only keeps one history per hypothesis. In addition, the size of a Hiero SCFG grammar is typically much larger than phrase-based models when extracted from the same data which also slows down decoding. In this thesis we address these issues in Hiero by adopting a new translation model and decoding algorithm called Left-to-Right hierarchical phrase-based translation (LR-Hiero for short). LR-Hiero uses a constrained form of lexicalized SCFG rules to encode translation, where the target-side is constrained to be prefix-lexicalized. LR-Hiero uses a decoding algorithm with time complexity O(n̂2) that generates the target language output in left-to-right manner which keeps only one history per hypothesis resulting in faster decoding for Hiero grammars. The thesis contains the following contributions: (i) We propose a novel dynamic programming algorithm for rule extraction phase. Unlike traditional Hiero rule extraction which performs a brute-force search, LR-Hiero rule extraction is linear in the number of rules. (ii) We propose an augmented version of LR-decoding algorithm previously proposed by (Watanabe+, ACL 2006). Our modified LR-decoding algorithm addresses issues related to decoding time and translation quality and is shown to be more efficient than the CKY decoding algorithm in our experimental results. (iii) We extend our LR-decoding algorithm to capture all hierarchical phrasal alignments that are reachable in CKY-style decoding algorithms. (iv) We introduce a lexicalized reordering model to LR-Hiero that significantly improves the translation quality. (v) We apply LR-Hiero to the task of simultaneous translation; the first attempt to use Hiero models in simultaneous translation. We show that we can perform online segmentation on the source side to improve latency and maintain translation quality.
Download or read book Machine Learning in Translation Corpora Processing written by Krzysztof Wolk and published by CRC Press. This book was released on 2019-02-25 with total page 205 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book reviews ways to improve statistical machine speech translation between Polish and English. Research has been conducted mostly on dictionary-based, rule-based, and syntax-based, machine translation techniques. Most popular methodologies and tools are not well-suited for the Polish language and therefore require adaptation, and language resources are lacking in parallel and monolingual data. The main objective of this volume to develop an automatic and robust Polish-to-English translation system to meet specific translation requirements and to develop bilingual textual resources by mining comparable corpora.
Download or read book Investigations on Hierarchical Phrase based Machine Translation written by David Vilar Torres and published by . This book was released on 2011 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Neural Machine Translation written by Philipp Koehn and published by Cambridge University Press. This book was released on 2020-06-18 with total page 410 pages. Available in PDF, EPUB and Kindle. Book excerpt: Deep learning is revolutionizing how machine translation systems are built today. This book introduces the challenge of machine translation and evaluation - including historical, linguistic, and applied context -- then develops the core deep learning methods used for natural language applications. Code examples in Python give readers a hands-on blueprint for understanding and implementing their own machine translation systems. The book also provides extensive coverage of machine learning tricks, issues involved in handling various forms of data, model enhancements, and current challenges and methods for analysis and visualization. Summaries of the current research in the field make this a state-of-the-art textbook for undergraduate and graduate classes, as well as an essential reference for researchers and developers interested in other applications of neural methods in the broader field of human language processing.
Download or read book Phrase Alignment Models for Statistical Machine Translation written by John Sturdy DeNero and published by . This book was released on 2010 with total page 210 pages. Available in PDF, EPUB and Kindle. Book excerpt: The goal of a machine translation (MT) system is to automatically translate a document written in some human input language (e.g., Mandarin Chinese) into an equivalent document written in an output language (e.g., English). This task--so simple in its specification, and yet so rich in its complexities--has challenged computer science researchers for 60 years. While MT systems are in wide use today, the problem of producing human-quality translations remains unsolved. Statistical approaches have substantially improved the quality of MT systems by effectively exploiting parallel corpora: large collections of documents that have been translated by people, and therefore naturally occur in both the input and output languages. Broadly characterized, statistical MT systems translate an input document by matching fragments of its contents to examples in a parallel corpus, and then stitching together the translations of those fragments into a coherent document in an output language. The central challenge of this approach is to distill example translations into reusable parts: fragments of sentences that we know how to translate robustly and are likely to recur. Individual words are certainly common enough to recur, but they often cannot be translated correctly in isolation. At the other extreme, whole sentences can be translated without much context, but rarely repeat, and so cannot be recycled to build new translations. This thesis focuses on acquiring translations of phrases: contiguous sequences of a few words that encapsulate enough context to be translatable, but recur frequently in large corpora. We automatically identify phrase-level translations that are contained within human-translated sentences by partitioning each sentence into phrases and aligning phrases across languages. This alignment-based approach to acquiring phrasal translations gives rise to statistical models of phrase alignment. A statistical phrase alignment model assigns a score to each possible analysis of a sentence-level translation, where an analysis describes which phrases within that sentence can be translated and how to translate them. If the model assigns a high score to a particular phrasal translation, we should be willing to reuse that translation in new sentences that contain the same phrase. Chapter 1 provides a non-technical introduction to phrase alignment models and machine translation. Chapter 2 describes a complete state-of-the-art phrase-based translation system to clarify the role of phrase alignment models. The remainder of this thesis presents a series of novel models, analyses, and experimental results that together constitute a thorough investigation of phrase alignment models for statistical machine translation. Chapter 3 presents the formal properties of the class of phrase alignment models, including inference algorithms and tractability results. We present two specific models, along with statistical learning techniques to fit their parameters to data. Our experimental evaluation identifies two primary challenges to training and employing phrase alignment models, and we address each of these in turn. The first broad challenge is that generative phrase models are structured to prefer very long, rare phrases. These models require external pressure to explain observed translations using small, reusable phrases rather than large, unique ones. Chapter 4 describes three Bayesian models and a corresponding Gibbs sampler to address this challenge. These models outperform the word-level models that are widely employed in research and production MT systems. The second broad challenge is structural: there are many consistent and coherent ways of analyzing a translated sentence using phrases. Long phrases, short phrases, and overlapping phrases can all simultaneously express correct, translatable units. However, no previous phrase alignment models have leveraged this rich structure to predict alignments. We describe a discriminative model of multi-scale, overlapping phrases that outperforms all previously proposed models. The cumulative result of this thesis is to establish model-based phrase alignment as the most effective approach to acquiring phrasal translations. Only phrase alignment models are able to incorporate statistical signals about multi-word constructions into alignment decisions and score coherent phrasal analyses of full sentence pairs. As a result, phrase alignment models outperform classical word-level models in both generative and discriminative settings. This result is fundamental to the field: the models proposed in this thesis address a general, language-independent alignment problem that arises in all state-of-the-art statistical machine translation systems in use today.
Download or read book Statistical Machine Translation written by Philipp Koehn and published by Cambridge University Press. This book was released on 2010 with total page 447 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Download or read book CCG augmented Hierarchical Phrase based Statistical Machine Translation written by Hala Almaghout and published by . This book was released on 2012 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Refinements in Hierarchical Phrase based Translation Systems written by Juan Miguel Pino and published by . This book was released on 2015 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Learning Machine Translation written by Cyril Goutte and published by MIT Press. This book was released on 2009 with total page 329 pages. Available in PDF, EPUB and Kindle. Book excerpt: How Machine Learning can improve machine translation: enabling technologies and new statistical techniques.
Download or read book Phrase Based Statistical Machine Translation written by Richard Zens and published by . This book was released on 2008 with total page 151 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Statistical Phrase Based Translation written by and published by . This book was released on 2003 with total page 8 pages. Available in PDF, EPUB and Kindle. Book excerpt: We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phase-based models out-performed word-based models. Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. Surprisingly, learning phrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems.
Download or read book Adjunction in Hierarchical Phrase based Translation written by Sophie Arnoult and published by . This book was released on 2021 with total page 124 pages. Available in PDF, EPUB and Kindle. Book excerpt:
