A central problem of natural language generation is that of 'expressibility'. Meteer presents a solution which uses a level of representation called the Text Structure, an intermediate between the representation of world and the language.

Rothkegel argues that text production is the result of interaction between text knowledge and object knowledge - the conventional ordering and presentation of knowledge for communicative purposes and the conceptual organisation of world knowledge.

This book records a unique attempt over a ten-year period to use stochastic optimization in the natural language processing domain. Setting the work against the background of the logical rule-based approach, the author provides a context for understanding the differences in assumptions about the nature of language and cognition.

The key assumption in this text is that machine translation is not merely a mechanical process but in fact requires a high level of linguistic sophistication, as the nuances of syntax, semantics and intonation cannot always be conveyed by modern technology. The increasing dependence on artificial communication by private and corporate users makes this research area an invaluable element when teaching linguistic theory.

Machine learning and data mining are inseparably connected with uncertainty. The observable data for learning is usually imprecise, incomplete or noisy. "Uncertainty Modeling for Data Mining: A Label Semantics Approach" introduces 'label semantics', a fuzzy-logic-based theory for modeling uncertainty. Several new data mining algorithms based on label semantics are proposed and tested on real-world datasets. A prototype interpretation of label semantics and new prototype-based data mining algorithms are also discussed. This book offers a valuable resource for postgraduates, researchers and other professionals in the fields of data mining, fuzzy computing and uncertainty reasoning.

Zengchang Qin is an associate professor at the School of Automation Science and Electrical Engineering, Beihang University, China; Yongchuan Tang is an associate professor at the College of Computer Science, Zhejiang University, China.

This book investigates the nature of generalization in language and examines how language is known by adults and acquired by children. It looks at how and why constructions are learned, the relation between their forms and functions, and how cross-linguistic and language-internal generalizations about them can be explained.
Constructions at Work is divided into three parts: in the first Professor Goldberg provides an overview of constructionist approaches, including the constructionist approach to argument structure, and argues for a usage-based model of grammar. In Part II she addresses issues concerning how generalizations are constrained and constructional generalizations are learned. In Part III the author shows that a combination of function and processing accounts for a wide range of language-internal and cross-linguistic generalizations. She then considers the degree to which the function of constructions explains their distribution and examines cross-linguistic tendencies in argument realization. She demonstrates that pragmatic and cognitive processes account for the data without appeal to stipulations that are language-specific.
This book is an important contribution to the study of how language operates in the mind and in the world and how these operations relate. It is of central interest for scholars and graduate-level students in all branches of theoretical linguistics and psycholinguistics. It will also appeal to cognitive scientists and philosophers concerned with language and its acquisition.

This book presents recent advances by leading researchers in computational modelling of language acquisition. The contributors, from departments of linguistics, cognitive science, psychology, and computer science, combine powerful computational techniques with real data and in doing so throw new light on the operations of the brain and the mind. They explore the extent to which linguistic structure is innate and/or available in a child's environment, and the degree to which language learning is inductive or deductive. They assess the explanatory power of different models. The book will appeal to all those working in language acquisition.

As spoken natural language dialog systems technology continues to make great strides, numerous issues regarding dialog processing still need to be resolved. This book presents an exciting new dialog processing architecture that allows for a number of behaviors required for effective human-machine interactions, including: problem-solving to help the user carry out a task, coherent subdialog movement during the problem-solving process, user model usage, expectation usage for contextual interpretation and error correction, and variable initiative behavior for interacting with users of differing expertise. The book also details how different dialog problems in processing can be handled simultaneously, and provides instructions and in-depth result from pertinent experiments. Researchers and professionals in natural language systems will find this important new book an invaluable addition to their libraries.

This book deals with the computational application of systemic functional grammar (SFG) for natural language generation. More particularly, it first describes the implementation of a fragment of the grammar of German in the computational framework of KOMET-PENMAN for multilingual generation. Second, it presents a specification of explicit well-formedness constraints on syntagmatic structure which are defined in the form of typed feature structures. It thus achieves a model of systemic functional grammar that unites both the stregths of systemics, such as stratification, functional diversification, the orientation to context etc., adn the kinds of syntactic generalizations that are typically found in modern, syntagmatically-focused computational grammars. Elke Teich worked as a researcher in the KOMET project for text generation at the German National Research Centre for Information Technology, Institute for Integrated Publication and Information Systems, Darmstadt from 1990 to 1996. She is now a Research Associate at the Institute for Applied Linguistics, Translating and Interpreting, University of the Saarland, Saarbrucken.

This book is a first-stop introduction to corpus-based language research. It takes the reader systematically through the practical problems and benefits including the points to be reviewed before using computers, obtaining corpus material, the main analytical tools and the most important applications of computerised natural language processing. Each chapter offers guidance on programming where appropriate at a level suitable for readers with no prior experience, and provides exercises to help the reader to apply the principles covered. Case studies are used to show how the techniques are used in genuine research situations. * Provides and introduction to computer analysis, techniques, the practical problems involved in using them and their potential benefits * The guidance on programming provides a basic tool kit for use and devleopment by readers with no previous experience. * The exercises at the end of each chapter allow readers to test their understanding and to develop an effective approach to their own research problems. * The case studies demonstrate the use of the techniques described in real research situations.

Fur Leser, die bereits die Grundlagen der Wissensverarbeitung und Computernetzwerke beherrschen, gibt das Buch einen UEberblick uber innovative Verfahren, die die automatisierte Suche, Recherche, Klassifikation und Verwaltung von Texten im Kontext dezentraler Systeme und vor allem im WWW erlauben. Besondere Aufmerksamkeit wird dabei auf eine personalisierte Verarbeitung gerichtet, die auch zeitliche Aspekte, wie z. B. das digitale Vergessen, einbeziehen. An vielen Stellen werden auf interessante und neuartige Art und Weise Analogien aus anderen Wissensgebieten, so z. B. zur Verarbeitung von Informationen und zum Lernen im menschlichen Gehirn sowie der Natur schlechthin genutzt.

How does a parser, a device that imposes an analysis on a string of symbols so that they can be interpreted, work? More specifically, how does the parser in the human cognitive mechanism operate? Using a wide range of empirical data concerning human natural language processing, Bradley Pritchett demonstrates that parsing performance depends on grammatical competence, not, as many have thought, on perception, computation, or semantics.
Pritchett critiques the major performance-based parsing models to argue that the principles of grammar drive the parser; the parser, furthermore, is the apparatus that tries to enforce the conditions of the grammar at every point in the processing of a sentence. In comparing garden path phenomena, those instances when the parser fails on the first reading of a sentence and must reanalyze it, with occasions when the parser successfully functions the first time around, Pritchett makes a convincing case for a grammar-derived parsing theory.

"Text Analysis with R for Students of Literature" is written with students and scholars of literature in mind but will be applicable to other humanists and social scientists wishing to extend their methodological tool kit to include quantitative and computational approaches to the study of text. Computation provides access to information in text that we simply cannot gather using traditional qualitative methods of close reading and human synthesis. "Text Analysis with R for Students of Literature" provides a practical introduction to computational text analysis using the open source programming language R. R is extremely popular throughout the sciences and because of its accessibility, R is now used increasingly in other research areas. Readers begin working with text right away and each chapter works through a new technique or process such that readers gain a broad exposure to core R procedures and a basic understanding of the possibilities of computational text analysis at both the micro and macro scale. Each chapter builds on the previous as readers move from small scale microanalysis of single texts to large scale macroanalysis of text corpora, and each chapter concludes with a set of practice exercises that reinforce and expand upon the chapter lessons. The book s focus is on making the technical palatable and making the technical useful and immediately gratifying."