Download or read book Latent Domain Models for Statistical Machine Translation written by Hoàng Cường and published by . This book was released on 2017 with total page 145 pages. Available in PDF, EPUB and Kindle. Book excerpt: "A data-driven approach to model translation suffers from the data mismatch problem and demands domain adaptation techniques. Given parallel training data originating from a specific domain, training an MT system on the data would result in a rather suboptimal translation for other domains. But does suboptimality of translation happen only in such an extreme scenario of domain mismatch? This dissertation shows that training SMT systems on heterogeneous corpora (e.g. EuroParl) may also result in suboptimal performance of statistical translation systems. Specifically, it is clear that a word/phrase could be translated in different ways when it comes to different domains. The translation statistics induced from word alignment models and phrase-based models, however, reflect translation preferences aggregated over diverse domains in heterogeneous corpora. In this sense, they can be considered as coarse and domain-confused statistics. This dissertation shows that domain-confused statistics may harm performance of both word alignment and phrase-based models. Another important contribution of this dissertation is to provide a principled way to address the problem. We focus on learning the translation statistics with respect to each of diverse domains (i.e. domain-focused translation statistics). With our method of domain induction for translation, we present a comprehensive study of domain adaptation for statistical machine translation, including four specific case studies Data Selection, Phrase-Based Translation, Word Alignment and Rewarding Domain Invariance in translation. Finally, we briefly describe Scorpio, the ILLC-UvA Adaptation System submitted to an adaptation task at WMT 2016, which participated with the language pair of English-Dutch. This system consolidates the ideas in the thesis on latent variable models for adaptation. Results validate the effective adaptation performance in a competitive setting."--Samenvatting auteur.
Download or read book Data Selection for Statistical Machine Translation written by Amittai Axelrod and published by . This book was released on 2014 with total page 124 pages. Available in PDF, EPUB and Kindle. Book excerpt: Machine translation, the computerized translation of one human language to another, could be used to communicate between the thousands of languages used around the world. Statistical machine translation (SMT) is an approach to building these translation engines without much human intervention, and large-scale implementations by Google, Microsoft, and Facebook in their products are used by millions daily. The quality of SMT systems depends on the example translations used to train the models. Data can come from a variety of sources, many of which are not optimal for common specific tasks. The goal is to be able to find the right data to use to train a model for a particular task. This work determines the most relevant subsets of these large datasets with respect to a translation task, enabling the construction of task-specific translation systems that are more accurate and easier to train than the large-scale models. Three methods are explored for identifying task-relevant translation training data from a general data pool. The first uses only a language model to score the training data according to lexical probabilities, improving on prior results by using a bilingual score that accounts for differences between the target domain and the general data. The second is a topic-based relevance score that is novel for SMT, using topic models to project texts into a latent semantic space. These semantic vectors are then used to compute similarity of sentences in the general pool to the target task. This work finds that what the automatic topic models capture for some tasks is actually the style of the language, rather than task-specific content words. This motivates the third approach, a novel style-based data selection method. Hybrid word and part-of-speech (POS) representations of the two corpora are constructed by retaining the discriminative words and using POS tags as a proxy for the stylistic content of the infrequent words. Language models based on these representations can be used to quantify the underlying stylistic relevance between two texts. Experiments show that style-based data selection can outperform the current state-of-the-art method for task-specific data selection, in terms of SMT system performance and vocabulary coverage. Taken together, the experimental results indicate that it is important to characterize corpus differences when selecting data for statistical machine translation.
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 Neural Machine Translation written by Philipp Koehn and published by Cambridge University Press. This book was released on 2020-06-18 with total page 409 pages. Available in PDF, EPUB and Kindle. Book excerpt: Learn how to build machine translation systems with deep learning from the ground up, from basic concepts to cutting-edge research.
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 Latent Structure Discriminative Learning for Natural Language Processing written by Ann Clifton and published by . This book was released on 2015 with total page 89 pages. Available in PDF, EPUB and Kindle. Book excerpt: Natural language is rich with layers of implicit structure, and previous research has shown that we can take advantage of this structure to make more accurate models. Most attempts to utilize forms of implicit natural language structure for natural language processing tasks have assumed a pre-defined structural analysis before training the task-specific model. However, rather than fixing the latent structure, we may wish to discover the latent structure that is most useful via feedback from an extrinsic task. The focus of this thesis is on jointly learning the best latent analysis along with the model for the NLP task we are interested in. In this work, we present a generalized learning framework for discriminative training overjointly learned latent structures, and apply this to several NLP tasks. We develop a high accuracy discriminative language model over shallow parse structures. We demonstrate an efficient algorithm for learning this grammaticality classifier by combining the input of multiple representations of the latent structures. Next, we set forth a framework for latent structure learning for statistical machine translation (SMT), in which the latent segmentation and alignment of the parallel training data inform the translation model. This model jointly optimizes segmentation and alignment for the translation task, novelly learning over latent representations of the input. We also propose a discriminative bilingual topic model over hierarchically structured latent topics, which allows for weighted contributions from more informative inputs and can be optimized for SMT. We apply this model to morphological disambiguation and domain adaptation for SMT. Finally, we give an investigation of large-scale distributed training for structured discriminative models and propose recommendations for distributed computational topologies.
Download or read book Linguistic Structure Prediction written by Noah A. Smith and published by Springer Nature. This book was released on 2022-05-31 with total page 248 pages. Available in PDF, EPUB and Kindle. Book excerpt: A major part of natural language processing now depends on the use of text data to build linguistic analyzers. We consider statistical, computational approaches to modeling linguistic structure. We seek to unify across many approaches and many kinds of linguistic structures. Assuming a basic understanding of natural language processing and/or machine learning, we seek to bridge the gap between the two fields. Approaches to decoding (i.e., carrying out linguistic structure prediction) and supervised and unsupervised learning of models that predict discrete structures as outputs are the focus. We also survey natural language processing problems to which these methods are being applied, and we address related topics in probabilistic inference, optimization, and experimental methodology. Table of Contents: Representations and Linguistic Data / Decoding: Making Predictions / Learning Structure from Annotated Data / Learning Structure from Incomplete Data / Beyond Decoding: Inference
Download or read book Exploiting Comparable Corpora for Domain specific Statistical Machine Translation written by Magdalena Plamadă 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 Machine Translation written by Muyun Yang and published by Springer. This book was released on 2017-01-05 with total page 135 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the 12th China Workshop on Machine Translation, CWMT 2016, held in Urumqi, China, in August 2016. The 10 English papers presented in this volume were carefully reviewed and selected from 76 submissions. They deal with statistical machine translation, hybrid machine translation, machine translation evaluation, post editing, alignment, and inducing bilingual knowledge from corpora.
Download or read book Alignment Models and Algorithms for Statistical Machine Translation written by James Jonathan Jesse Brunning and published by . This book was released on 2010 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Download or read book Natural Language Processing and Chinese Computing written by Ming Zhou and published by Springer. This book was released on 2012-11-05 with total page 310 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the First CCF Conference, NLPCC 2012, held in Beijing, China, during October/November, 2012. The 43 revised full papers presented were carefully reviewed and selected from 151 submissions. The papers are organized in topical sections on applications on language computing; fundamentals on language computing; machine translation and multi-lingual information access; NLP for search, ads and social networks; question answering and Web mining.
Download or read book Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016 written by Aboul Ella Hassanien and published by Springer. This book was released on 2016-10-20 with total page 933 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book gathers the proceedings of the 2nd International Conference on Advanced Intelligent Systems and Informatics (AISI2016), which took place in Cairo, Egypt during October 24–26, 2016. This international interdisciplinary conference, which highlighted essential research and developments in the field of informatics and intelligent systems, was organized by the Scientific Research Group in Egypt (SRGE) and sponsored by the IEEE Computational Intelligence Society (Egypt chapter) and the IEEE Robotics and Automation Society (Egypt Chapter). The book’s content is divided into four main sections: Intelligent Language Processing, Intelligent Systems, Intelligent Robotics Systems, and Informatics.
Download or read book Natural Language Processing and Chinese Computing written by Guodong Zhou and published by Springer. This book was released on 2013-10-01 with total page 450 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the Second CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2013, held in Chongqing, China, during November 2013. The 31 revised full papers presented together with three keynote talks and 13 short papers were carefully reviewed and selected from 203 submissions. The papers are organized in topical sections on fundamentals on language computing; applications on language computing; machine learning for NLP; machine translation and multi-lingual information access; NLP for social media and web mining, knowledge acquisition; NLP for search technology and ads; NLP fundamentals; NLP applications; NLP for social media.
Download or read book Multilingual Natural Language Processing Applications written by Daniel Bikel and published by IBM Press. This book was released on 2012-05-11 with total page 829 pages. Available in PDF, EPUB and Kindle. Book excerpt: Multilingual Natural Language Processing Applications is the first comprehensive single-source guide to building robust and accurate multilingual NLP systems. Edited by two leading experts, it integrates cutting-edge advances with practical solutions drawn from extensive field experience. Part I introduces the core concepts and theoretical foundations of modern multilingual natural language processing, presenting today’s best practices for understanding word and document structure, analyzing syntax, modeling language, recognizing entailment, and detecting redundancy. Part II thoroughly addresses the practical considerations associated with building real-world applications, including information extraction, machine translation, information retrieval/search, summarization, question answering, distillation, processing pipelines, and more. This book contains important new contributions from leading researchers at IBM, Google, Microsoft, Thomson Reuters, BBN, CMU, University of Edinburgh, University of Washington, University of North Texas, and others. Coverage includes Core NLP problems, and today’s best algorithms for attacking them Processing the diverse morphologies present in the world’s languages Uncovering syntactical structure, parsing semantics, using semantic role labeling, and scoring grammaticality Recognizing inferences, subjectivity, and opinion polarity Managing key algorithmic and design tradeoffs in real-world applications Extracting information via mention detection, coreference resolution, and events Building large-scale systems for machine translation, information retrieval, and summarization Answering complex questions through distillation and other advanced techniques Creating dialog systems that leverage advances in speech recognition, synthesis, and dialog management Constructing common infrastructure for multiple multilingual text processing applications This book will be invaluable for all engineers, software developers, researchers, and graduate students who want to process large quantities of text in multiple languages, in any environment: government, corporate, or academic.
Download or read book Mobile Speech and Advanced Natural Language Solutions written by Amy Neustein and published by Springer Science & Business Media. This book was released on 2013-02-03 with total page 373 pages. Available in PDF, EPUB and Kindle. Book excerpt: "Mobile Speech and Advanced Natural Language Solutions" presents the discussion of the most recent advances in intelligent human-computer interaction, including fascinating new study findings on talk-in-interaction, which is the province of conversation analysis, a subfield in sociology/sociolinguistics, a new and emerging area in natural language understanding. Editors Amy Neustein and Judith A. Markowitz have recruited a talented group of contributors to introduce the next generation natural language technologies for practical speech processing applications that serve the consumer’s need for well-functioning natural language-driven personal assistants and other mobile devices, while also addressing business’ need for better functioning IVR-driven call centers that yield a more satisfying experience for the caller. This anthology is aimed at two distinct audiences: one consisting of speech engineers and system developers; the other comprised of linguists and cognitive scientists. The text builds on the experience and knowledge of each of these audiences by exposing them to the work of the other.
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 264 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 Triplet Lexicon Models for Statistical Machine Translation written by Saša Hasan and published by . This book was released on 2011 with total page 147 pages. Available in PDF, EPUB and Kindle. Book excerpt:
