Verbmobil Foundations Of Speech To Speech Translation

In 1992 it seemed very difficult to answer the question whether it would be possible to develop a portable system for the automatic recognition and translation of spon taneous speech. Previous research work on speech processing had focused on read speech only and international projects aimed at automated text translation had just been terminated without achieving their objectives. Within this context, the German Federal Ministry of Education and Research (BMBF) made a careful analysis of all national and international research projects conducted in the field of speech and language technology before deciding to launch an eight-year basic-research lead project in which research groups were to cooperate in an interdisciplinary and international effort covering the disciplines of computer science, computational linguistics, translation science, signal processing, communi cation science and artificial intelligence. At some point, the project comprised up to 135 work packages with up to 33 research groups working on these packages. The project was controlled by means of a network plan. Every two years the project sit uation was assessed and the project goals were updated. An international scientific advisory board provided advice for BMBF. A new scientific approach was chosen for this project: coping with the com plexity of spontaneous speech with all its pertinent phenomena such as ambiguities, self-corrections, hesitations and disfluencies took precedence over the intended lex icon size. Another important aspect was that prosodic information was exploited at all processing stages.

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.

Parsing can be defined as the decomposition of complex structures into their constituent parts, and parsing technology as the methods, the tools, and the software to parse automatically. Parsing is a central area of research in the automatic processing of human language. Parsers are being used in many application areas, for example question answering, extraction of information from text, speech recognition and understanding, and machine translation. New developments in parsing technology are thus widely applicable. This book contains contributions from many of today's leading researchers in the area of natural language parsing technology. The contributors describe their most recent work and a diverse range of techniques and results. This collection provides an excellent picture of the current state of affairs in this area. This volume is the third in a series of such collections, and its breadth of coverage should make it suitable both as an overview of the current state of the field for graduate students, and as a reference for established researchers.

This book describes a complete translation system for spontaneously spoken language, constructed using the incremental paradigm. It starts by presenting the theoretical and algorithmic basis necessary to cope with the complex endeavour of translating speech incrementally and in parallel. In particular, graph-theoretic foundations of natural language processing and feature-based descriptions of linguistic objects are covered. A thorough description of the system and its performance follows. The author covers syntactic and semantic processing as well as transfer and syntactic generation. Thus the book can also be used as a broad-coverage introduction to the field of speech translation. This book is essential reading for researchers and students working in the field of speech translation. It is also intended as a research tool for those interested in the architecture of general natural language processing systems.

Natural Language Processing (NLP) is a scientific discipline which is found at the intersection of fields such as Artificial Intelligence, Linguistics, and Cognitive Psychology. This book presents in four chapters the state of the art and fundamental concepts of key NLP areas. Are presented in the first chapter the fundamental concepts in lexical semantics, lexical databases, knowledge representation paradigms, and ontologies. The second chapter is about combinatorial and formal semantics. Discourse and text representation as well as automatic discourse segmentation and interpretation, and anaphora resolution are the subject of the third chapter. Finally, in the fourth chapter, I will cover some aspects of large scale applications of NLP such as software architecture and their relations to cognitive models of NLP as well as the evaluation paradigms of NLP software. Furthermore, I will present in this chapter the main NLP applications such as Machine Translation (MT), Information Retrieval (IR), as well as Big Data and Information Extraction such as event extraction, sentiment analysis and opinion mining.

The Verbmobil System currently under development in Germany would input speech in a source language dialogue, translate it, and output synthesized speech in a target language, all in real time under the conditions of face-to-face dialogue. This preliminary study is an assessment of the state of the art of the speech recognition and machine translation fields, and a frank discussion of the challenges the developers of such a system face. A speech-based machine translation system in effect combines all the technical problems of understanding and generation systems and adds the very special difficulties of translation. The difficulties of translation are illustrated with a variety of examples culled from a number of languages. A general architecture called translation-by-negotiation is proposed. This book is of value not only to students of speech recognition and machine translation, but to anyone interested in natural language processing in general, since computational problems and linguistic approaches at various levels of linguistics and analysis are discussed.

The Routledge Encyclopedia of Translation Technology provides a state-of-the art survey of the field of computer-assisted translation. It is the first definitive reference to provide a comprehensive overview of the general, regional and topical aspects of this increasingly significant area of study. The Encyclopedia is divided into three parts: Part One presents general issues in translation technology, such as its history and development, translator training and various aspects of machine translation, including a valuable case study of its teaching at a major university; Part Two discusses national and regional developments in translation technology, offering contributions covering the crucial territories of China, Canada, France, Hong Kong, Japan, South Africa, Taiwan, the Netherlands and Belgium, the United Kingdom and the United States Part Three evaluates specific matters in translation technology, with entries focused on subjects such as alignment, bitext, computational lexicography, corpus, editing, online translation, subtitling and technology and translation management systems. The Routledge Encyclopedia of Translation Technology draws on the expertise of over fifty contributors from around the world and an international panel of consultant editors to provide a selection of articles on the most pertinent topics in the discipline. All the articles are self-contained, extensively cross-referenced, and include useful and up-to-date references and information for further reading. It will be an invaluable reference work for anyone with a professional or academic interest in the subject.

A volume of selected, annotated references arranged under specific headings to provide a non-partisan guide to teachers involved in designing courses in translation and/or interpreting.