Teaching computers how to translate from one human language into another is an ongoing research topic in computer science. This book explains the fundamental ideas on which statistical machine translation is based and what you need to get a real statistical machine translation system running. The core of this book is focused on different strategies that will help you minimize the time needed to train your system and to get the best translation possible. We pose the question whether it is primarily the size of your training corpus that determines the quality of translation or if there are other ways that can boost the quality of the translated text as well. What is the best approach to deal with morphologically rich languages? How important is the genre of the text? We use tools like Moses, MGIZA, SRILM and perform empirical analyses to answer these questions.
Turkic communities come from a common culture; however the interaction with other communities over years caused diversion especially in written language. A system which can automatically translate documents written in different Turkic languages will be an important step towards eliminating the disunity of Turkic communities on written work of art over past ninety years and obtaining fusion of Turkic communities. In this book, a rule-based and semi-supervised machine translation system "MT-Turk", which is designed for closely related Turkic languages and implemented on Turkish, Kirghiz and Kazan Tatar, is presented. MT-Turk is an extensible bidirectional translation infrastructure in which new Turkic dialects can be added by just adding the lexicon of roots/stems, suffixes, and the rules. Furthermore, it is open to extension by suggestion. In order to form a multilingual machine translation infrastructure, two subsets of rule-based approach, the interlingual machine translation approach and transfer-based approach were used in combination to achieve extensibility and interoperability. The book also includes evaluation of the translation process using both BLEU and NIST metrics.
This study makes substantial contributions to both the theoretical and computational treatment of information structure, with a specific focus on creating natural language processing applications such as multilingual machine translation systems. The present study first provides cross-linguistic findings in regards to information structure meanings and markings. Building upon such findings, the current model represents information structure within the HPSG/MRS framework using Individual Constraints. The primary goal of the present study is to create a multilingual grammar model of information structure for the LinGO Grammar Matrix system. The present study explores the construction of a grammar library for creating customized grammar incorporating information structure and illustrates how the information structure-based model improves performance of transfer-based machine translation.
This book constitutes the referred proceedings of the 4th Conference of the Association for Machine Translation in the Americas, AMTA 2000, held in Cuernavaca, Mexico in October 2000. The 18 technical papers, seven system descriptions, and three user studies presented were carefully reviewed and selected for inclusion in the book. All current issues of machine translations, ranging from theoretical and foundational issues to systems evaluation and case studies, are addressed.
Inspired by widespread convergent phenomena, this book attempts to study translation from the perspective of global convergence. With concrete examples of both linguistic and cultural convergence, the interdependent relationships respectively between language and culture and between translation and convergence are explored as prerequisites for elaborating on the focal theme. Then, based on an irresistible tendency of convergence and worldwide linguistic and cultural crises, the book goes a step further to focus on analyzing proper cross-culture translation strategies by putting forward relevant translation principles and detailed translation techniques with vivid examples. For better understanding and further reference, major factors influencing the choice of translation strategies are illustrated and the translator is suggested to make a cautious and comprehensive decision of the most practical approach. The research should be especially useful to those who are interested or engaged in translation studies.
Translation Quality Assessment; a Model Revisited written in 1997 is based on Hallidayan systemic-functional theory, but also draws eclectically on Prague school ideas, speech act theory, pragmatics, discourse analysis and corpus-based distinctions between spoken and written language (House, 1997), is of those contrastive studies of House works. Translation quality assessment is based on the investigation of two main divisions of linguistic features. The first captures the field, tenor, mode and genre and then the second one is about being overt or covert translation which is concluded based on the features of first division. This book investigates the matter of cultural filtering which is one of those problematic features in translation and other factors as mentioned above. However, the purpose is not only to understand what is the problem or preference but also is to reach a deep understanding of this issue according to this model.
Thesis (M.A.) from the year 2011 in the subject Interpreting / Translating , grade: A, University of Gdansk (Institute of English), course: Translation studies, language: English, abstract: Humour translation is an extremely difficult process which causes translators many problems. Rendering humour into a different language becomes even more complicated when the translator translates film dialogues for the purpose of dubbing or subtitling. The aim of this thesis is to analyse translation strategies and techniques applied in the process of humour translation in dubbing and subtitling. The analysis is based on two animated films: Shrek 2 and Ice Age. In the thesis the original version of film dialogues is compared with its dubbed and subtitled versions in Polish. The material for the study comes from DVD releases. The thesis is divided into two chapters. In the first chapter the concept of humour is explained and humour translation is described. In this chapter I also provide definitions of translation strategy and translation technique, explain the difference between these two concepts and describe possible translation strategies and techniques in humour translation. In the second part of the first chapter the specificity of audiovisual translation is discussed, and subtitling and dubbing are described as two different translation methods.The second chapter offers a comparison between the Polish dubbed and subtitled dialogue versions. In this chapter I describe translation str...