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.
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.
This volume provides an in-depth comparative study of translation practices and the role of the poet-translator across different countries and in so doing, demonstrates the need for poetry translation to be extended beyond close reading and situated in context. Drawing on a corpus composed of data from national library catalogues and Worldcat, the book examines translation practices of English-language, French-language, and Italian-language poet-translators through the lens of a broad sociological approach. Chapters 2 through 5 look at national poetic movements, literary markets, and the historical and socio-political contexts of translations, with Chapter 6 offering case studies of prominent and representative poet-translators from each tradition. A comprehensive set of appendices offers readers an opportunity to explore this data in greater detail. Taken together, the volume advocates for the need to study translation data against broader aesthetic, historical, and political trends and will be of particular interest to students and scholars in translation studies and comparative literature.
The purpose of this thesis is to try to show that certain moment conditions are essential for the admissibility of various 'good' translation invariant statistical procedures. Section 3 indicates the inadmissibility of a unique best translation invariant estimate if a certain moment condition fails to be satisfied. Section 4 and 5 shows, by example, the inadmissibility of a best translation invariant test if either the test is non-unique or certain moment conditions fail to hold. Section 6 shows, by example, that a certain translation invariant confidence interval is inadmissible if a certain moment condition fails to hold.