The KBMT Project


Book Description

Machine translation of natural languages is one of the most complex and comprehensive applications of computational linguistics and artificial intelligence. This is especially true of knowledge-based machine translation (KBMT) systems, which require many knowledge resources and processing modules to carry out the necessary levels of analysis, representation and generation of meaning and form. The number of real-world problems, tasks, and solutions involved in developing any realistic-size knowledge-based machine translation system is enormous. It is thus difficult for researchers in the field to learn what a system "really does". This book fills that need with a detailed case study of a KBMT system implemented at the Center for Machine Translation at Carnegie Mellon University. The research consists in part of the creation of a system for translation between English and Japanese. The corpora used in the project were manuals for installing and maintaining IBM personal computers (sponsorship by IBM, through its Tokyo Research Laboratory) Individual chapters describe the interlingua texts used in knowledge-based machine translation, the grammar formalism embodied in the system, the grammars and lexicons and their roles in the translation process, the process of source language analysis, an augmentation module that interactively and automatically resolves ambiguities remaining after source language analysis, and the generator, which produces target language sentences. Detailed appendices illustrate the process from analysis through generation. This book is intended for developers, researchers and advanced students in natural language processing and computational linguistics, including all those who have an interest in machine translation and machine-aided translation.




Knowledge Systems and Translation


Book Description

It is generally agreed that knowledge plays an important role in translation and interpreting and that it should therefore be of central concern to translation and interpreting studies. However, there is no general agreement about what is actually meant by the term 'knowledge' in this context, nor about in exactly what ways it is relevant. Also, present-day translation and interpreting studies offer only a limited amount of research specifically dedicated to knowledge systematization and other knowledge-related issues. This book is one of the first to systematically and exclusively address the question of knowledge in translation and interpreting. It is a collection of papers by leading scholars both from the field of translation and interpreting and from adjacent fields where knowledge also plays an important role, such as linguistics and computer science. The experts present a wide variety of conceptions of knowledge and a number of different approaches to the study of knowledge in translation and interpreting: some of them draw on concepts such as scenes and frames, mental spaces and semantic networks, some discuss knowledge systems from an ontological point of view, and some present more general concepts of knowledge in translation and interpreting. Along the same lines, some of the contributors deal mainly with theoretical and conceptual aspects, others focus on methodological issues, and again others report on empirical studies. What brings them together, however, is their common focus on the interface between knowledge and translation/interpreting, and their main achievement is that, by joining forces, they manage to present to their readers a state-of-the-art report which offers both a clearer delimitation of the concept of knowledge and a better understanding of its role in translation and interpreting.




Status of Machine Translation (MT) Technology


Book Description




Compositional Translation


Book Description

This book provides an in-depth review of machine translation by discussing in detail a particular method, called compositional translation, and a particular system, Rosetta, which is based on this method. The Rosetta project is a unique combination of fundamental research and large-scale implementation. The book covers all scientifically interesting results of the project, highlighting the advantages of designing a translation system based on a relation between reversible compositional grammars. The power of the method is illustrated by presenting elegant solutions to a number of well-known translation problems. The most outstanding characteristic of the book is that it provides a firm linguistic foundation for machine translation. For this purpose insights from Montague Grammar are integrated with ideas developed within the Chomskyan tradition, in a computationally feasible framework. Great care has been taken to introduce the basic concepts of the underlying disciplines to the uninitiated reader, which makes the book accessible to a wide audience, including linguists, computer scientists, logicians and translators.




Routledge Encyclopedia of Translation Studies


Book Description

Praise for the previous edition of the Encyclopedia of Translation Studies: 'Translation has long deserved this sort of treatment. Appropriate for any college or university library supporting a program in linguistics, this is vital in those institutions that train students to become translators.' – Rettig on Reference 'Congratulations should be given to Mona Baker for undertaking such a mammoth task and...successfully pulling it off. It will certainly be an essential reference book and starting point for anyone interested in translation studies.' – ITI Bulletin 'This excellent volume is to be commended for bringing together some of [its] most recent research. It provides a series of extremely useful short histories, quite unlike anything that can be found elsewhere. University teachers will find it invaluable for preparing seminars and it will be widely used by students.' – The Times Higher Education Supplement ' ... a pioneering work of reference ...'– Perspectives on Translation The Routledge Encyclopedia of Translation Studies has been the standard reference in the field since it first appeared in 1998. The second, extensively revised and extended edition brings this unique resource up-to-date and offers a thorough, critical and authoritative account of one of the fastest growing disciplines in the humanities. The Encyclopedia is divided into two parts and alphabetically ordered for ease of reference. Part One (General) covers the conceptual framework and core concerns of the discipline. Categories of entries include: central issues in translation theory (e.g. equivalence, translatability, unit of translation) key concepts (e.g. culture, norms, ethics, ideology, shifts, quality) approaches to translation and interpreting (e.g. sociological, linguistic, functionalist) types of translation (e.g. literary, audiovisual, scientific and technical) types of interpreting (e.g. signed language, dialogue, court). New additions in this section include entries on globalisation, mobility, localization, gender and sexuality, censorship, comics, advertising and retranslation, among many others. Part Two (History and Traditions) covers the history of translation in major linguistic and cultural communities. It is arranged alphabetically by linguistic region. There are entries on a wide range of languages which include Russian, French, Arabic, Japanese, Chinese and Finnish, and regions including Brazil, Canada and India. Many of the entries in this section are based on hitherto unpublished research. This section includes one new entry: Southeast Asian tradition. Drawing on the expertise of over 90 contributors from 30 countries and an international panel of consultant editors, this volume offers a comprehensive overview of translation studies as an academic discipline and anticipates new directions in the field. The contributors examine various forms of translation and interpreting as they are practised by professionals today, in addition to research topics, theoretical issues and the history of translation in various parts of the world. With key terms defined and discussed in context, a full index, extensive cross-references, diagrams and a full bibliography the Routledge Encyclopedia of Translation Studies is an invaluable reference work for all students and teachers of translation, interpreting, and literary and social theory. Mona Baker is Professor of Translation Studies at the University of Manchester, UK. She is co-founder and editorial director of St Jerome Publishing, a small press specializing in translation studies and cross-cultural communication. Apart from numerous papers in scholarly journals and collected volumes, she is author of In Other Words: A Coursebook on Translation (Routledge 1992), Translation and Conflict: A Narrative Account (2006) and Founding Editor of The Translator: Studies in Intercultural Communication (1995), a refereed international journal published by St Jerome since 1995. She is also co-Vice President of the International Association of Translation and Intercultural Studies (IATIS). Gabriela Saldanha is Lecturer in Translation Studies at the University of Birmingham, UK. She is founding editor (with Marion Winters) and current member of the editorial board of New Voices in Translation Studies, a refereed online journal of the International Association of Translation and Intercultural Studies, and co-editor (with Federico Zanettin) of Translation Studies Abstracts and Bibliography of Translation Studies.




Intelligent Language Tutors


Book Description

The techniques of natural language processing (NLP) have been widely applied in machine translation and automated message understanding, but have only recently been utilized in second language teaching. This book offers both an argument for and a critical examination of this new application, with an examination of how systems may be designed to exploit the power of NLP, accomodate its limitations, and minimize its risks. This volume marks the first collection of work in the U.S. and Canada that incorporates advanced human language technologies into language tutoring systems, covering languages as diverse as Arabic, Spanish, Japanese, and English. The book is organized into sections that express the levels of analysis dealt with in learning and teaching a language and with the tasks of the student as writer, reader, conversant, and actor in the world. These sections bring together research by specialists in linguistics, artificial intelligence, psychology, instructional design, and language teaching. In addition to providing detailed descriptions of working systems, amply illustrated with screens from lesson and authoring interfaces, the contributors address a spectrum of common issues: * What can current NLP technology contribute to computer-assisted language instruction and to research on language learning? * How can this technology meet the demands of pedagogical theory for communicative language teaching in authentic contexts? * How can designers constrain tutoring environments to ensure accurate analysis of learners' language? * What can NLP-based systems teach us about language acquisition, about linguistic theory, and about theories of language pedagogy? * What lessons have been learned in using these systems to date? Discipline-specific issues are illuminated as well: the relative merits of the major syntactic frameworks for NLP-based language tutoring; the adaptation of theories like lexical conceptual structure to support semantic interpretation; the integration of input language with visual microworlds and dialogue games; the pragmatics of the tutoring discourse; the selection of instructional principles to guide system design; and the accomodation of design to individual differences and learner styles. A concluding section assesses this work from larger theoretical and practical perspectives -- experimental psychology and psycholinguistics, linguistics, language teaching, and second language acquisition research.







Computational Linguistics and Intelligent Text Processing


Book Description

CICLing 2005 (www.CICLing.org) was the 6th Annual Conference on Intelligent Text Processing and Computational Linguistics. It was intended to provide a balanced view of the cutting-edge developments in both the theoretical foundations of computational linguistics and the practice of natural-language text processing with its numerous applications. A feature of CICLing conferences is their wide scope that covers nearly all areas of computational linguistics and all aspects of natural language processing applications. This year we were honored by the presence of our keynote speakers Christian Boitet (CLIPS-IMAG, Grenoble), Kevin Knight (ISI), Daniel Marcu (ISI), and Ellen Riloff (University of Utah), who delivered excellent extended lectures and organized vivid discussions and encouraging tutorials; their invited papers are published in this volume. Of 151 submissions received, 88 were selected for presentation; 53 as full papers and 35 as short papers, by exactly 200 authors from 26 countries: USA (15 papers); Mexico (12); China (9.5); Spain (7.5); South Korea (5.5); Singapore (5); Germany (4.8); Japan (4); UK (3.5); France (3.3); India (3); Italy (3); Czech Republic (2.5); Romania (2.3); Brazil, Canada, Greece, Ireland, Israel, the Netherlands, Norway, Portugal, Sweden, Switzerland (1 each); Hong Kong (0.5); and Russia (0.5) including the invited papers. Internationally co-authored papers are counted in equal fractions.




Trends in Natural Language Generation - An Artificial Intelligence Perspective


Book Description

This proceedings volume gives an up-to-date overview of the most recent results in the field of plant molecular response to environmental constraints, especially heat, cold, water/drought, salt or light. It centers on molecular approaches in understanding the bases of plant tolerance to physical stresses, links among different environmental stresses, and the manipulation of gene expression by recombinant DNA technology to obtain tolerant transgenic plants.




Encyclopedia of Library and Information Science


Book Description

"The Encyclopedia of Library and Information Science provides an outstanding resource in 33 published volumes with 2 helpful indexes. This thorough reference set--written by 1300 eminent, international experts--offers librarians, information/computer scientists, bibliographers, documentalists, systems analysts, and students, convenient access to the techniques and tools of both library and information science. Impeccably researched, cross referenced, alphabetized by subject, and generously illustrated, the Encyclopedia of Library and Information Science integrates the essential theoretical and practical information accumulating in this rapidly growing field."