Product Description
With the rising importance of multilingualism in languageindustries, brought about by global markets and world-wide informationexchange, parallel corpora, i.e. corpora of texts accompanied by theirtranslation, have become key resources in the development of naturallanguage processing tools. The applications based upon parallelcorpora are numerous and growing in number: multilingual lexicographyand terminology, machine and human translation, cross-languageinformation retrieval, language learning, etc.
The book's chapters have been commissioned from major figures in thefield of parallel corpus building and exploitation, with the aim ofshowing the state of the art in parallel text alignment and use ten tofifteen years after the first parallel-text alignment techniques weredeveloped. Within the book, the following broad themes are addressed:(i) techniques for the alignment of parallel texts at various levelssuch as sentence, clause, and word; (ii) the use of parallel texts infields as diverse as translation, lexicography, and informationretrieval; (iii) available corpus resources and the evaluation ofalignment methods.
The book will be of interest to researchers and advanced students ofcomputational linguistics, terminology, lexicography and translation,both in academia and industry. ... Read more

Product Description

Bridging the gap between the needs of the technical engineer and cognitive researchers related to speech technology applications. 

Systematic approach focusing on the utility of speech related product design

Designed to respond to the growing need for specific theories, tools and methods for design, testing and evaluating speech related human-system interfaces.

Targeted at designers, engineers, and decision makers working in the area of speech technology research

Product Description
This work presents the state-of-the-art in speech science and technology in Japan. Recent developments in the field have been grouped in five chapters, covering the main developments during the past decade. The development of various speech input/output devices and their practical applications is described. Use of digital signal processing, a new method for analyzing speech, and the use of LSIs for speech input/output, have been contributed to the present achievements in the field of speech acoustics. ... Read more

Product Description
The 1990s have been an exciting time for researchers workingwith large collections of text. Text is available like never before.It was not all that long ago that researchers referred to the BrownCorpus as a `large' corpus. The Brown Corpus, a `mere' million wordscollected at Brown University in the 1960s, is about the same size asa dozen novels, the complete works of William Shakespeare, the Bible,a collegiate dictionary or a week of a newswire service. Today, onecan easily surf the web and download millions of words in no time atall. What can we do with all this data? It is better to do something simplethan nothing at all. Researchers in large corpora are using basicallybrute force methods to make progress on some of the hardest problemsin natural language processing, including part-of-speech tagging, wordsense disambiguation, parsing, machine translation, informationretrieval, and discourse analysis. They are overcoming the so-calledknowledge-acquisition bottleneck by processing vast quantities ofdata, more text than anyone could possibly read in a lifetime, andestimating all sorts of `central and typical' facts that any speakerof the language would be expected to know, e.g. word frequencies, wordassociations and typical predicate--argument relations. Much of this work has been reported at a series of annual meetings,known as the Workshop on Very Large Corpora (WVLC) and relatedmeetings sponsored by ACL/SIGDAT (Association for ComputationalLinguistics' special interest group on data). Subsequent meetings havebeen held in Asia (1994, 1997), America (1995, 1996, 1997) and Europe(1995, 1996). The papers in this book represent much of the best ofthe first three years of this workshop/conference as selected by acompetitive review process. ... Read more

Product Description
This volume presents papers in English and German looking at the area of language processing and speech technology. The following subjects were discussed: modelling, cognition, perception and behaviour; langauge and speech systems; multilingual research and developments; prosody; syntax, morphology, lexicon; semantics; formalisms and parsing; and tools for development and teaching. ... Read more

Product Description
Focusing on human computers via speech technology, this title covers such issues as dialogue, design, error correction, feedback and the use of speech technology with other I/O media (keyboards, mice, touch screens etc). Although the application of speech technology is not widespread, "Interactive Speech Technology" contends that human factors/ergonomics input could radically change this, by developing ways in which speech technology can be made truly interactive. This book focuses on three main areas - recognition, production and dialogue. Contributions come from centres of excellence in both academia and industry, and presents a state of the art review, opening up a forum for discussion on fundamental issues which should survive the inevitable changes in actual hard and software technologies. ... Read more

Product Description
Parsing technology is concerned with finding syntacticstructure in language. In parsing we have to deal with incomplete andnot necessarily accurate formal descriptions of natural languages.Robustness and efficiency are among the main issuesin parsing. Corpora can be used to obtain frequency information about languageuse. This allows probabilistic parsing, an approach that aims at bothrobustness and efficiency increase. Approximation techniques, to beapplied at the level of language description, parsing strategy, andsyntactic representation, have the same objective. Approximation atthe level of syntactic representation is also known asunderspecification, a traditional technique to deal with syntacticambiguity.

In this book new parsing technologies are collected that aim atattacking the problems of robustness and efficiency by exactly thesetechniques: the design of probabilistic grammars and efficientprobabilistic parsing algorithms, approximation techniques applied togrammars and parsers to increase parsing efficiency, and techniquesfor underspecification and the integration of semantic information inthe syntactic analysis to deal with massive ambiguity. The book gives a state-of-the-art overview of current research anddevelopment in parsing technologies. In its chapters we see howprobabilistic methods have entered the toolbox of computationallinguistics in order to be applied in both parsing theory and parsingpractice. The book is both a unique reference for researchers and anintroduction to the field for interested graduate students. ... Read more

Product Description

This book addresses the interests of a large community of researchers in the fields of XML-based annotation techniques and corpus-based language technology. It covers the most significant recent developments in this field, from multi-layered mark-up and standards to theoretical formalisms to applications. The contributions are based on research projects at international level in text technology, computational linguistics, hypertext modeling and in the domain of standards and tools for language resources. Core topics are: strategies for multi-layered document modeling and processing, mark-up at different levels for textual resources, and text-technological information modeling.

The sections of the book offer an exhaustive coverage of many of the current topics in the fields concerned, especially: Multi-layered Markup; Markup Languages and Language Resources; Markup and Text Types; Markup Languages and Hypertext; Markup and Formalization.

The book may be seen as a contribution to very ambitious goals, connected to the development of an ‘Annotation Science’ (a term recently coined by Nancy Ide), as for example the interoperability of different types of linguistic and textual resources, of corpora and processing tools, as well as the development of methods and annotation techniques applicable to multiple modalities and languages.

Product Description

This book describes the framework of inductive dependency parsing, a methodology for robust and efficient syntactic analysis of unrestricted natural language text. Coverage includes a theoretical analysis of central models and algorithms, and an empirical evaluation of memory-based dependency parsing using data from Swedish and English. A one-stop reference to dependency-based parsing of natural language, it will interest researchers and system developers in language technology, and is suitable for graduate or advanced undergraduate courses.

Product Description

This book assembles major writings in speech production and phonetics of the pioneering Gunnar Fant, along with his more recent work on speech prosody. The book reviews the stages of the speech chain, covering production, speech data analysis and speech perception. 19 selected articles are grouped in 6 chapters, including a historical outline plus Speech production and synthesis; The voice source; Speech analysis and features; Speech perception; Prosody.

Product Description
This book offers a state-of-the-art survey of methods andtechniques for structuring, acquiring and maintaining lexicalresources for speech and language processing.
The first chapter provides a broad survey of the field ofcomputational lexicography, introducing most of the issues, terms andtopics which are addressed in more detail in the rest of the book. Thenext two chapters focus on the structure and the content of man-madelexicons, concentrating respectively on (morpho-)syntactic and(morpho-)phonological information. Both chapters adopt a declarativeconstraint-based methodology and pay ample attention to the variousways in which lexical generalizations can be formalized and exploitedto enhance the consistency and to reduce the redundancy of lexicons. Acomplementary perspective is offered in the next two chapters, whichpresent techniques for automatically deriving lexical resources fromtext corpora. These chapters adopt an inductive data-orientedmethodology and focus also on methods for tokenization, lemmatizationand shallow parsing. The next three chapters focus on speechapplications, more specifically on the organization of speech databases, and on the use of lexica in speech synthesis and speechrecognition. The last chapter takes a psycholinguistic perspective andaddresses the relation between storage and computation in the mentallexicon.
The relevance of these topics for speech and language processing isobvious, for since NLP systems need large lexica in order to achievereasonable coverage, and since the construction and maintenance oflarge-size lexical resources is a complex and costly task, it is ofcrucial importance for those who design or build such systems to beaware of the latest developments in this fast-moving field.
The intended audience for this book includes advanced students andprofessional scientists working in the areas of computationallinguistics and language and speech technology. ... Read more

Product Description
With the rising importance of multilingualism in languageindustries, brought about by global markets and world-wide informationexchange, parallel corpora, i.e. corpora of texts accompanied by theirtranslation, have become key resources in the development of naturallanguage processing tools. The applications based upon parallelcorpora are numerous and growing in number: multilingual lexicographyand terminology, machine and human translation, cross-languageinformation retrieval, language learning, etc. The book's chapters have been commissioned from major figures in thefield of parallel corpus building and exploitation, with the aim ofshowing the state of the art in parallel text alignment and use ten tofifteen years after the first parallel-text alignment techniques weredeveloped. Within the book, the following broad themes are addressed:(i) techniques for the alignment of parallel texts at various levelssuch as sentence, clause, and word; (ii) the use of parallel texts infields as diverse as translation, lexicography, and informationretrieval; (iii) available corpus resources and the evaluation ofalignment methods. The book will be of interest to researchers and advanced students ofcomputational linguistics, terminology, lexicography and translation,both in academia and industry. ... Read more

Product Description
Speech is probably the one most important feature which distinguishes humans from other animals. This book is concerned with giving the power of speech to machines, and thereby giving disabled people the power to communicate, which they would otherwise lack.

Synthetic speech is used in two ways by disabled people: as a replacement for natural speech; and as a means of communicating complex information to people who cannot receive it by other means, such as blindcomputer users. This book covers both forms of use, showing the features they have in common, but separating the differences.

It is accessible both to readers with a technical background, and also to those with less such experience, thanks to an extensive glossary. It is a valuable resource and includes information on available products.

Product Description
Time Map Phonology addresses key areas of sound structureat which the two technologies of natural language processing andspeech technology are beginning to converge. Solutions are presentedto the problems of how to process words which have not been heardbefore and how to develop fine-grained knowledge representation andprocessing techniques for linguistic units smaller than the word. Thesolutions are based on a careful comparison of linguistic theories andon the investigation of computational techniques for the nextgeneration of flexible spoken language input and output devices. Theapproach has been fully implemented for the vocabulary of German andsubjected to quantitative evaluation. ... Read more

Product Description

This volume deals with a wide range of topics including the representation of tones and intonation, evidence for and constraints on prosodic phrasing, prosodic boundary detection, articulatory dynamics of stress, timing in speech, and prosodic correlates of speaking style, as well as the perception of prosodic prominence. The book offers investigators in all areas of speech communication a comprehensive and coherent presentation of contemporary prosodic research.

Product Description

In its nine chapters, this book provides an overview of the state-of-the-art and best practice in several sub-fields of evaluation of text and speech systems and components. The evaluation aspects covered include speech and speaker recognition, speech synthesis, animated talking agents, part-of-speech tagging, parsing, and natural language software like machine translation, information retrieval, question answering, spoken dialogue systems, data resources, and annotation schemes. With its broad coverage and original contributions this book is unique in the field of evaluation of speech and language technology.

This book is of particular relevance to advanced undergraduate students, PhD students, academic and industrial researchers, and practitioners.

Product Description
Written by the world's top experts in the field, this multidisciplinary book explores all phases of speech technology. Topics covered include:·Conversion of computerized (keyboarded) text into synthesized speech, aimed at developing "talking computers"·Development of automatic speech recognition, allowing electronic devices to process verbal commands·Speech training and the use of synthesized speech for the hearing- and speech-impaired·In-depth discussions of specific speech technologies are included, as well as a treatment of the issues and challenges of human-computer interfaces. Oriented toward state-of-the-art applications, the book emphasizes the practical utilization of emerging technologies and includes numerous case studies. ... Read more

Product Description
Corpus-based methods will be found at the heart of manylanguage and speech processing systems. This book provides an in-depthintroduction to these technologies through chapters describing basicstatistical modeling techniques for language and speech, the use ofHidden Markov Models in continuous speech recognition, the developmentof dialogue systems, part-of-speech tagging and partial parsing,data-oriented parsing and n-gram language modeling.
The book attempts to give both a clear overview of the maintechnologies used in language and speech processing, along withsufficient mathematics to understand the underlying principles. Thereis also an extensive bibliography to enable topics of interest to bepursued further. Overall, we believe that the book will give newcomersa solid introduction to the field and it will give existingpractitioners a concise review of the principal technologies used instate-of-the-art language and speech processing systems.
Corpus-Based Methods in Language and Speech Processing is aninitiative of ELSNET, the European Network in Language and Speech. Inits activities, ELSNET attaches great importance to the integration oflanguage and speech, both in research and in education. The need forand the potential of this integration are well demonstrated by thispublication. ... Read more