This collection examines the promise and limitations for computer-assisted language learning of emerging speech technologies: speech recognition, text-to-speech synthesis, and acoustic visualization. Using pioneering research from contributors based in the US and Europe, this volume illustrates the uses of each technology for learning languages, the problems entailed in their use, and the solutions evolving in both technology and instructional design. To illuminate where these technologies stand on the path from research toward practice, the book chapters are organized to reflect five stages in the maturation of learning technologies: basic research, analysis of learners' needs, adaptation of technologies to meet needs, development of prototypes to incorporate adapted technologies, and evaluation of prototypes. The volume demonstrates the progress in employing each class of speech technology while pointing up the effort that remains for effective, reliable application to language learning.

The rapid advancement in the theoretical understanding of statistical and machine learning methods for semisupervised learning has made it difficult for nonspecialists to keep up to date in the field. Providing a broad, accessible treatment of the theory as well as linguistic applications, Semisupervised Learning for Computational Linguistics offers self-contained coverage of semisupervised methods that includes background material on supervised and unsupervised learning. The book presents a brief history of semisupervised learning and its place in the spectrum of learning methods before moving on to discuss well-known natural language processing methods, such as self-training and co-training. It then centers on machine learning techniques, including the boundary-oriented methods of perceptrons, boosting, support vector machines (SVMs), and the null-category noise model. In addition, the book covers clustering, the expectation-maximization (EM) algorithm, related generative methods, and agreement methods. It concludes with the graph-based method of label propagation as well as a detailed discussion of spectral methods. Taking an intuitive approach to the material, this lucid book facilitates the application of semisupervised learning methods to natural language processing and provides the framework and motivation for a more systematic study of machine learning.

This book investigates the language of Polish-English bilingual children raised in the United Kingdom and their Polish monolingual counterparts. It exemplifies the lexico-grammatical knowledge of both groups and uses corpus-based grammatical inference in order to establish the source of the impediment of the minority language of the bilingual group. The author applies the methodology of corpus linguistics and narrative analysis to study the language of young bilinguals. He presupposes the caveat that a child-type competence exists and can be contrasted with an adult-type competence. He uses a variety of corpus frequency measures to compare the specific stylometric features of bilingual child narratives and their monolingual counterparts. The book focuses on how bilingual and monolingual language differs in areas such as the lexicon, morphosyntax, and semantics.

Language and Computers introduces students to the fundamentals of how computers are used to represent, process, and organize textual and spoken information. Concepts are grounded in real-world examples familiar to students experiences of using language and computers in everyday life. * A real-world introduction to the fundamentals of how computers process language, written specifically for the undergraduate audience, introducing key concepts from computational linguistics. * Offers a comprehensive explanation of the problems computers face in handling natural language * Covers a broad spectrum of language-related applications and issues, including major computer applications involving natural language and the social and ethical implications of these new developments * The book focuses on real-world examples with which students can identify, using these to explore the technology and how it works * Features under-the-hood sections that give greater detail on selected advanced topics, rendering the book appropriate for more advanced courses, or for independent study by the motivated reader.

This 1992 collection takes the exciting step of examining natural language phenomena from the perspective of both computational linguistics and formal semantics. Computational linguistics has until now been primarily concerned with the construction of computational models for handling the complexities of linguistic form, but has not tackled the questions of representing or computing meaning. Formal semantics, on the other hand, has attempted to account for the relations between forms and meanings, without necessarily attending to computational concerns. The book introduces the reader to the two disciplines and considers the prospects for the more unified and comprehensive computational theory of language which might obtain from their amalgamation. Of great interest to those working in the fields of computation, logic, semantics, artificial intelligence and linguistics generally.

One of the most hotly debated phenomena in natural language is that of leftward argument scrambling. This book investigates the properties of Hindi-Urdu scrambling to show that it must be analyzed as uniformly a focality-driven XP-adjunction operation. It proposes a novel theory of binding and coreference that not only derives the coreference effects in scrambled constructions, but has important consequences for the proper formulation of binding, crossover, reconstruction, and representational economy in the minimalist program. The book will be of interest not only to specialists in Hindi-Urdu syntax and/or scrambling, but to all students of generative syntax.

This volume explores multiple dimensions of openness in ICT-enhanced education. The chapters, contributed by researchers and academic teachers, present a number of exemplary solutions in the area. They involve the use of open source software, innovative technologies, teaching/learning methods and techniques, as well as examine potential benefits for both teachers' and students' cognitive, behavioural and metacognitive development.

The development of smaller and more powerful computers and the introduction of new communication channels by the interlinking of computers, by the Internet and the World Wide Web, have caused great changes for linguistics. They affect the methods in the various disciplines of pure linguistics as well as the tools and ways of applied linguistics such as translation and interpretation, language teaching, learning, and testing. This volume presents general reflections and overview articles on these new developments by noted experts followed by reports on the concrete uses of information technologies for linguistic purposes in different European countries and at the European Parliament. A discussion of another important linguistic issue is added: the various uses of the highly symbolic term national language.

Users of natural languages have many word orders with which to encode the same truth-conditional meaning. They choose contextually appropriate strings from these many ways with little conscious effort and with effective communicative results. Previous computational models of when English speakers produce non-canonical word orders, like topicalization, left-dislocation, and clefts, fail-either by overgenerating these statistically rare forms or by undergenerating. The primary goal of this book is to present a better model of when speakers choose to produce certain non-canonical word orders by incorporating the effects of discourse context and speaker goals on syntactic choice. The theoretical model is then used as a basis for building a probabilistic classifier that can select the most human-like word order based on the surrounding discourse context. The model of discourse context used is a methodological advance both from a theoretical and an engineering perspective. It is built up from individual linguistic features, ones more easily and reliably annotated than the direct annotation of a discourse or rhetorical structure for a text. This book makes extensive use of previously unexamined naturally occurring corpus data of non-canonical word order in English, both to illustrate the points of the theoretical model and to train the statistical model.

This book is an introduction to the rudiments of Perl programming. It provides the general reader with an interest in language with the most usable and relevant aspects of Perl for writing programs that deal with language.Through a series of simple examples and exercises, the reader is gradually introduced to the essentials of good programming. The examples are carefully constructed to make the introduction of new concepts as simple as possible, while at the same time using sample programs that make sense to someone who works with language as data. Many of these programs can be used immediately with minimal or no modification. The text is accompanied by exercises at the end of each chapter and all the code is available from the companion website: http: //www .u.arizona.edu/~hammond.

Computers offer new perspectives in the study of language, allowing us to see phenomena that previously remained obscure because of the limitations of our vantage points. It is not uncommon for computers to be likened to the telescope, or microscope, in this respect. In this pioneering computer-assisted study of translation, Dorothy Kenny suggests another image, that of the kaleidoscope: playful changes of perspective using corpus-processing software allow textual patterns to come into focus and then recede again as others take their place. And against the background of repeated patterns in a corpus, creative uses of language gain a particular prominence.

In Lexis and Creativity in Translation, Kenny monitors the translation of creative source-text word forms and collocations uncovered in a specially constructed German-English parallel corpus of literary texts. Using an abundance of examples, she reveals evidence of both normalization and ingenious creativity in translation. Her discussion of lexical creativity draws on insights from traditional morphology, structural semantics and, most notably, neo-Firthian corpus linguistics, suggesting that rumours of the demise of linguistics in translation studies are greatly exaggerated.

Lexis and Creativity in Translation is essential reading for anyone interested in corpus linguistics and its impact so far on translation studies. The book also offers theoretical and practical guidance for researchers who wish to conduct their own corpus-based investigations of translation. No previous knowledge of German, corpus linguistics or computing is assumed.

This comprehensive reference work provides an overview of the concepts, methodologies, and applications in computational linguistics and natural language processing (NLP). * Features contributions by the top researchers in the field, reflecting the work that is driving the discipline forward * Includes an introduction to the major theoretical issues in these fields, as well as the central engineering applications that the work has produced * Presents the major developments in an accessible way, explaining the close connection between scientific understanding of the computational properties of natural language and the creation of effective language technologies * Serves as an invaluable state-of-the-art reference source for computational linguists and software engineers developing NLP applications in industrial research and development labs of software companies

Contemporary corpus linguists use a wide variety of methods to study discourse patterns. This volume provides a systematic comparison of various methodological approaches in corpus linguistics through a series of parallel empirical studies that use a single corpus dataset to answer the same overarching research question. Ten contributing experts each use a different method to address the same broadly framed research question: In what ways does language use in online Q+A forum responses differ across four world English varieties (India, Philippines, United Kingdom, and United States)? Contributions will be based on analysis of the same 400,000 word corpus from online Q+A forums, and contributors employ methodologies including corpus-based discourse analysis, audience perceptions, Multi-Dimensional analysis, pragmatic analysis, and keyword analysis. In their introductory and concluding chapters, the volume editors compare and contrast the findings from each method and assess the degree to which 'triangulating' multiple approaches may provide a more nuanced understanding of a research question, with the aim of identifying a set of complementary approaches which could arguably take into account analytical blind spots. Baker and Egbert also consider the importance of issues such as researcher subjectivity, type of annotation, the limitations and affordances of different corpus tools, the relative strengths of qualitative and quantitative approaches, and the value of considering data or information beyond the corpus. Rather than attempting to find the 'best' approach, the focus of the volume is on how different corpus linguistic methodologies may complement one another, and raises suggestions for further methodological studies which use triangulation to enrich corpus-related research.

Polysemy is a term used in semantic and lexical analysis to describe a word with multiple meanings. The problem is to establish whether its the same word with related meanings or different words that happen to look or sound the same. In 'Plainly planes plane plains plainly' how many distinct lexical items are there? Such words present few difficulties in everyday language, but pose near-intractable problems for linguists and lexicographers. The contributors, including Anna Wierzbicka, Charles Fillmore, and James Pustejovsky, consider the implications of these problems for grammatical theory and how they may be addressed in computational linguistics.

This book focuses mainly on logical approaches to computational linguistics, but also discusses integrations with other approaches, presenting both classic and newly emerging theories and applications.Decades of research on theoretical work and practical applications have demonstrated that computational linguistics is a distinctively interdisciplinary area. There is convincing evidence that computational approaches to linguistics can benefit from research on the nature of human language, including from the perspective of its evolution. This book addresses various topics in computational theories of human language, covering grammar, syntax, and semantics. The common thread running through the research presented is the role of computer science, mathematical logic and other subjects of mathematics in computational linguistics and natural language processing (NLP). Promoting intelligent approaches to artificial intelligence (AI) and NLP, the book is intended for researchers and graduate students in the field.

Multi-Dimensional Analysis: Research Methods and Current Issues provides a comprehensive guide both to the statistical methods in Multi-Dimensional Analysis (MDA) and its key elements, such as corpus building, tagging, and tools. The major goal is to explain the steps involved in the method so that readers may better understand this complex research framework and conduct MD research on their own. Multi-Dimensional Analysis is a method that allows the researcher to describe different registers (textual varieties defined by their social use) such as academic settings, regional discourse, social media, movies, and pop songs. Through multivariate statistical techniques, MDA identifies complementary correlation groupings of dozens of variables, including variables which belong both to the grammatical and semantic domains. Such groupings are then associated with situational variables of texts like information density, orality, and narrativity to determine linguistic constructs known as dimensions of variation, which provide a scale for the comparison of a large number of texts and registers. This book is a comprehensive research guide to MDA.

This collection of papers and abstracts stems from the third meeting in the series of Sperlonga workshops on Cognitive Models of Speech Processing. It presents current research on the structure and organization of the mental lexicon, and on the processes that access that lexicon. The volume starts with discussion of issues in acquisition and consideration of questions such as, 'What is the relationship between vocabulary growth and the acquisition of syntax?', and, 'How does prosodic information, concerning the melodies and rhythms of the language, influence the processes of lexical and syntactic acquisition?'. From acquisition, the papers move on to consider the manner in which contemporary models of spoken word recognition and production can map onto neural models of the recognition and production processes. The issue of exactly what is recognised, and when, is dealt with next - the empirical findings suggest that the function of something to which a word refers is accessed with a different time-course to the form of that something. This has considerable implications for the nature, and content, of lexical representations. Equally important are the findings from the studies of disordered lexical processing, and two papers in this volume address the implications of these disorders for models of lexical representation and process (borrowing from both empirical data and computational modelling). The final paper explores whether neural networks can successfully model certain lexical phenomena that have elsewhere been assumed to require rule-based processes.

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.

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.

This book explains how to build Natural Language Generation (NLG) systems--computer software systems that automatically generate understandable texts in English or other human languages. NLG systems use knowledge about language and the application domain to automatically produce documents, reports, explanations, help messages, and other kinds of texts. The book covers the algorithms and representations needed to perform the core tasks of document planning, microplanning, and surface realization, using a case study to show how these components fit together. It is essential reading for researchers interested in NLP, AI, and HCI; and for developers interested in advanced document-creation technology.

The Language of ICT: * explores the nature of the electronic word and presents the new types of text in which it is found * examines the impact of the rapid technological change we are living through * analyses different texts, including email and answerphone messages, webpages, faxes, computer games and articles about IT * provides detailed guidance on downloading material from the web, gives URLs to visit, and includes a dedicated webpage * includes a comprehensive glossary of terms.

The book provides an overview of more than a decade of joint R&D efforts in the Low Countries on HLT for Dutch. It not only presents the state of the art of HLT for Dutch in the areas covered, but, even more importantly, a description of the resources (data and tools) for Dutch that have been created are now available for both academia and industry worldwide.

The contributions cover many areas of human language technology (for Dutch): corpus collection (including IPR issues) and building (in particular one corpus aiming at a collection of 500M word tokens), lexicology, anaphora resolution, a semantic network, parsing technology, speech recognition, machine translation, text (summaries) generation, web mining, information extraction, and text to speech to name the most important ones.

The book also shows how a medium-sized language community (spanning two territories) can create a digital language infrastructure (resources, tools, etc.) as a basis for subsequent R&D. At the same time, it bundles contributions of almost all the HLT research groups in Flanders and the Netherlands, hence offers a view of their recent research activities.

Targeted readers are mainly researchers in human language technology, in particular those focusing on Dutch. It concerns researchers active in larger networks such as the CLARIN, META-NET, FLaReNet and participating in conferences such as ACL, EACL, NAACL, COLING, RANLP, CICling, LREC, CLIN and DIR ( both in the Low Countries), InterSpeech, ASRU, ICASSP, ISCA, EUSIPCO, CLEF, TREC, etc. In addition, some chapters are interesting for human language technology policy makers and even for science policy makers in general.

"

The research described in this book shows that conversation analysis can effectively model dialogue. Specifically, this work shows that the multidisciplinary field of communicative ICALL may greatly benefit from including Conversation Analysis. As a consequence, this research makes several contributions to the related research disciplines, such as conversation analysis, second-language acquisition, computer-mediated communication, artificial intelligence, and dialogue systems. The book will be of value for researchers and engineers in the areas of computational linguistics, intelligent assistants, and conversational interfaces.

Semantic fields are lexically coherent - the words they contain co-occur in texts. In this book the authors introduce and define semantic domains, a computational model for lexical semantics inspired by the theory of semantic fields. Semantic domains allow us to exploit domain features for texts, terms and concepts, and they can significantly boost the performance of natural-language processing systems. Semantic domains can be derived from existing lexical resources or can be acquired from corpora in an unsupervised manner. They also have the property of interlinguality, and they can be used to relate terms in different languages in multilingual application scenarios. The authors give a comprehensive explanation of the computational model, with detailed chapters on semantic domains, domain models, and applications of the technique in text categorization, word sense disambiguation, and cross-language text categorization. This book is suitable for researchers and graduate students in computational linguistics.

Solving linguistic problems not infrequently reduces to carrying out tasks that are computationally complex and therefore requires automation. In such situations, the difference between having and not having computational tools to handle the tasks is not a matter of economy of time and effort, but may amount to the difference between finding and not finding a solution at all. The book is an introduction to machine-aided linguistic discovery, a novel research area, arguing for the fruitfulness of the computational approach by presenting a basic conceptual apparatus and several intelligent discovery programmes. One of the systems models the fundamental Saussurian notion of system, and thus, for the first time, after almost a century after the introduction of this concept and structuralism in general, linguists are capable to handle adequately this recurring computationally complex task. Another system models the problem of searching for Greenbergian language universals and is capable of stating its discoveries in an intelligible form, viz. a comprehensive English language text, thus constituting the first computer program to generate a whole scientific article. Yet another system detects potential inconsistencies in genetic language classifications. The programmes are applied with noteworthy results to substantial problems from diverse linguistic disciplines such as structural semantics, phonology, typology and historical linguistics.