The essays in this interdisciplinary book cover a range of implementations and designs, from formal computational models to large-scale NL processing systems.Natural language (NL) refers to human language-complex, irregular, diverse, with all its philosophical problems of meaning and context. Setting a new direction in AI research, this book explores the development of knowledge representation and reasoning (KRR) systems that simulate the role of NL in human information and knowledge processing. Traditionally, KRR systems have incorporated NL as an interface to an expert system or knowledge base that performed tasks separate from NL processing. As this book shows, however, the computational nature of representation and inference in NL makes it the ideal level for all tasks in an intelligent computer system. NL processing combines the qualitative characteristics of human knowledge processing with a computer's quantitative advantages, allowing for in-depth, systematic processing of vast amounts of information. The essays in this interdisciplinary book cover a range of implementations and designs, from formal computational models to large-scale NL processing systems.ContributorsSyed S. Ali, Bonnie J. Dorr, Karen Ehrlich, Robert Givan, Susan M. Haller, Sanda Harabagiu, Chung Hee Hwang, Lucja Iwanska, Kellyn Kruger, Naveen Mata, David A. McAllester, David D. McDonald, Susan W. McRoy, Dan Moldovan, William J. Rapaport, Lenhart Schubert, Stuart C. Shapiro, Clare R. Voss

In "Speaking," Willem "Pim" Levelt, Director of the Max-Planck-Institut fur Psycholinguistik, accomplishes the formidable task of covering the entire process of speech production, from constraints on conversational appropriateness to articulation and self-monitoring of speech. Speaking is unique in its balanced coverage of all major aspects of the production of speech, in the completeness of its treatment of the entire speech process, and in its strategy of exemplifying rather than formalizing theoretical issues."

Das Buch erklart die wesentlichen Ansatze zur Sprachsynthese und zur Spracherkennung und vermittelt die dafur relevanten Grundlagen. Dazu gehoeren insbesondere: Grundkenntnisse uber die menschliche Sprachproduktion und Sprachwahrnehmung Eigenschaften von Sprachsignalen und ihre Darstellung Grundkenntnisse in Linguistik, insbes. Phonetik, Morphologie und Syntax die wichtigsten Transformationen und Methoden der digitalen Sprachsignalverarbeitung statistische Ansatze zur Beschreibung vieldimensionaler Groessen und komplexer Zusammenhange (Hidden-Markov-Modelle und neuronale Netze) Formulierung und Anwendung von Wissen in der Form von Regeln Die 2. Auflage des Buches enthalt ein neues Kapitel uber die polyglotte Sprachsynthese, die gemischtsprachigen Text korrekt vorlesen kann. Zusatzlich werden sowohl fur die Sprachsignalproduktion als auch fur die Spracherkennung die neusten Ansatze eingefuhrt.Die ZielgruppenDieses gut lesbare Buch wendet sich insbesondere an Studierende im Bereich Sprachverarbeitung. Das Buch geht auch auf viele praktische Probleme ein, die beim Konzipieren von sprachverarbeitenden Systemen zu loesen sind. Ein ausfuhrliches Glossar und eine Internet-basierte Sammlung von Hoerbeispielen, Illustrationen und UEbungen erganzen das Buch.

Wikis sind webbasierte Anwendungen, die es allen Nutzern ermAglichen, Seiten nicht nur zu betrachten, sondern auch zu Andern. Angeregt durch die Internet-EnzyklopAdie Wikipedia entdecken immer mehr private Nutzer und Kleinorganisationen, aber auch Unternehmen die vielfAltigen AnwendungsmAglichkeiten von Wikis. Durch einfachen Aufbau und unkomplizierte Bedienung stellen sie eine ernstzunehmende Alternative zu teuren Content-Management-Systemen dar und bilden die Grundlage fA1/4r eine FA1/4lle von Anwendungen im Bereich der kooperativen Arbeit.

Das Buch beschreibt den praktischen Einsatz von Wikis zur DurchfA1/4hrung von Projekten sowohl fA1/4r Anwender als auch fA1/4r Betreiber. Dies umfasst eine schrittweise EinfA1/4hrung in die Philosophie und Funktionsweise, einen Aoeberblick A1/4ber Bedienelemente und Komponenten sowie die Installation und Konfiguration der Wiki-Klone MediaWiki, TWiki und Confluence-Wiki. Am Beispiel einer Konferenzplanung werden die EinsatzmAglichkeiten der Software als Projekttool dargestellt.

Acta Numerica is an annual publication containing invited survey papers by leading researchers in numerical mathematics and scientific computing. The papers present overviews of recent developments in their area and provide state-of-the-art techniques and analysis.

Empirical translation studies is a rapidly evolving research area. This volume, written by world-leading researchers, demonstrates the integration of two new research paradigms: socially-oriented and data driven approaches to empirical translation studies. These two models expand current translation studies and stimulate reader debates around how development of quantitative research methods and integration with advances in translation technologies would significantly increase the research capacities of translation studies. Highly engaging, the volume pioneers the development of socially-oriented innovative research methods to enhance the current research capacities of theoretical (descriptive) translation studies in order to tackle real-life research issues, such as environmental protection and multicultural health promotion. Illustrative case studies are used, bringing insight into advanced research methodologies of designing, developing and analysing large scale digital databases for multilingual and/or translation research.

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.

This book discusses various aspects of text data mining. Unlike other books that focus on machine learning or databases, it approaches text data mining from a natural language processing (NLP) perspective. The book offers a detailed introduction to the fundamental theories and methods of text data mining, ranging from pre-processing (for both Chinese and English texts), text representation and feature selection, to text classification and text clustering. It also presents the predominant applications of text data mining, for example, topic modeling, sentiment analysis and opinion mining, topic detection and tracking, information extraction, and automatic text summarization. Bringing all the related concepts and algorithms together, it offers a comprehensive, authoritative and coherent overview. Written by three leading experts, it is valuable both as a textbook and as a reference resource for students, researchers and practitioners interested in text data mining. It can also be used for classes on text data mining or NLP.

Deep reinforcement learning (DRL) is the combination of reinforcement learning (RL) and deep learning. It has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine, and famously contributed to the success of AlphaGo. Furthermore, it opens up numerous new applications in domains such as healthcare, robotics, smart grids and finance. Divided into three main parts, this book provides a comprehensive and self-contained introduction to DRL. The first part introduces the foundations of deep learning, reinforcement learning (RL) and widely used deep RL methods and discusses their implementation. The second part covers selected DRL research topics, which are useful for those wanting to specialize in DRL research. To help readers gain a deep understanding of DRL and quickly apply the techniques in practice, the third part presents mass applications, such as the intelligent transportation system and learning to run, with detailed explanations. The book is intended for computer science students, both undergraduate and postgraduate, who would like to learn DRL from scratch, practice its implementation, and explore the research topics. It also appeals to engineers and practitioners who do not have strong machine learning background, but want to quickly understand how DRL works and use the techniques in their applications.

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.

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.

This book aims to inform researchers with an interest in natural language generation about advances in the field. It is organised around four topics - system architectures, content planning, discourse planning and realisation in linguistic form - and it presents some of the most important works in this area of research.

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.

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.