Der Kongress "Verarbeitung Naturlicher Sprache" (KONVENS) ist die erste Tagung, die gemeinsam von den folgenden wissenschaftlichen Gesellschaften veranstaltet wird: GI (Gesellschaft fur Informa- tik e.V., Fachausschuss 1.3 "Naturliche Sprache"), DGfS (Deutsche Gesellschaft fur Sprachwissen- schaft / Sektion Computerlinguistik), GLDV (Gesellschaft fur Linguistische Datenverarbeitung), ITG/DEGA (Informationstechnische Gesellschaft in Zusammenarbeit mit der Deutschen Gesell- schaft fur Akustik) und OGAI (Osterreichische Gesellschaft fur Artificial Intelligence). Sie soll die erste in einer Reihe von Tagungen uber die Verarbeitung naturlicher Sprache im deutschsprachigen Raum s~n, die die beteiligten Gesellschaften in zweijahrigem Turnus planen. Die Verantwortung fur die Organisation werden die veranstaltenden Gesellschaften reihum ubernehmen; bei der KONVENS 92 hat die Gesellschaft fur Informatik die Federfuhrung. Die KONVENS hat das Ziel, einen Querschnitt durch die aktuelle Forschung in allen Gebieten der Sprachverarbeitung zu bieten. Hierzu ist die Mitwirkung samtlicher fur die Sprachverarbeitung relevanten Disziplinen, wie z.B. Informatik, Linguistik, Psychologie und Nachrichtentechnik, erfor- derlich. In den Beitragen sollen neben grundlagen-orientierten Forschungsaspekten und Resultaten auch innovative Anwendungen vertreten sein. Besonders erwunscht sind Berichte uber erfolgreich durchgefuhrte und implementierte Vorhaben. Zusatzlich sollen durch die Vorgabe eines Schwerpunktthemas Anstosse in wichtigen Forschungsrich- tungen vermittelt werden. Als Schwerpunktthema fur die KONVENS 92 wurde "Integration akustischer und linguistischer Ansatze" gewahlt. Zum Schwerpunktthema werden drei eingeladene Vortrage angeboten sowie zwei Einfuh- rungskurse, die der Tagung vorangehen.

This volume presents the proceedings of the Sixth International Workshop on Automated Natural Language Generation held in Castel Ivano, Trento, Italy, April 5-7, 1992. Besides an invited lecture by Nadia Magnenat-Thalmann, a well-known researcher in computer animation, on creating and visualizing speech and emotion, the volume includes the 17 thouroughly reviewed papers accepted for presentation, selected out of the submissions to the Workshop, as well as 11 statements contributed to panels on multilinguality and generation or extending language generation to multiple media. The accepted papers by leading researchers from Japan, North America and Europe fall in sections on generator system architecture, issues in realisation, issues in discourse structure, and beyond traditional generation.

Humans do a great job of reading text, identifying key ideas, summarizing, making connections, and other tasks that require comprehension and context. Recent advances in deep learning make it possible for computer systems to achieve similar results. Deep Learning for Natural Language Processing teaches you to apply deep learning methods to natural language processing (NLP) to interpret and use text effectively. In this insightful book, NLP expert Stephan Raaijmakers distills his extensive knowledge of the latest state-of-the-art developments in this rapidly emerging field. Key features An overview of NLP and deep learning * Models for textual similarity * Deep memory-based NLP * Semantic role labeling * Sequential NLP Audience For those with intermediate Python skills and general knowledge of NLP. No hands-on experience with Keras or deep learning toolkits is required. About the technology Natural language processing is the science of teaching computers to interpret and process human language. Recently, NLP technology has leapfrogged to exciting new levels with the application of deep learning, a form of neural network-based machine learning Stephan Raaijmakers is a senior scientist at TNO and holds a PhD in machine learning and text analytics. He's the technical coordinator of two large European Union-funded research security-related projects. He's currently anticipating an endowed professorship in deep learning and NLP at a major Dutch university.

In den letzten Jahren hat sich in der Informatik und speziell auch in der K}nstlichen Intelligenz ein Wandel in der Auffassung vom Computer und seinerVerwendung vollzogen - von der Vorstellung von der sequentiell arbeitenden Funktionseinheit zum verteilten, interaktiven, parallel arbeitenden System von Agenten/Akteuren. Computer werden also nicht nur als pers-nliches Werkzeug, sondern als Medien f}r Kommunikation und als einer unter vielen intelligenten Partnern in einer verteilten Arbeitsumgebung verwendet. Dieser Band beinhaltet alle Beitr{ge des 4. Internationalen GI-Kongre es "Wissensbasierte Systeme," der sich haupts{chlich mit dem f}r den praktischen Einsatz der Wissensverarbeitung {u erst wichtigen Themenkreis der verteilten K}nstlichen Intelligenz und der Unterst}tzung kooperativen Entscheidens und Handelns sowie mit eng verwandten Gebieten wie Wissensrepr{sentation, Mensch-Maschine-Interaktion und nat}rlich-sprachlichen Systemen befa te. Weitere Schwerpunkte des Kongre es waren die Theorie und Anwendung neuronaler Netze, wobei alle BMFT-Verbundprojekte zur Neuroinformatik vorgestellt wurden, sowie das in letzter Zeit f}r die Modellierung technischer Systeme immer n}tzlicher gewordene gebiet des qualitativen modellbasierten Schlie ens.

Die 7. \sterreichische Artificial-Intelligence-Tagung fand vom 24.-27. September 1991 an der Technischen Universit{t Wien statt. Sie hat aufgrund der starken Beteiligung aus dem Ausland einen ausgepr{gt internationalen Charakter, weshalb auch der vorliegende Tagungsband zweisprachig herausgegeben wurde. Die behandelten Themen aus dem Gebiet der K}nstlichen Intelligenz (KI) werden repr{sentiert durch sechzehn begutachtete Beitr{ge sowie zwei eingeladene Vortr{ge. Sie sind thematisch breit gestreut, wobei sich gewisse Schwerpunkte in den Gebieten "Nat}rliche Sprache" und "Wissensbasierte Systeme" sowie Logik und Schlie en" abzeichnen.

Text and Context: Document Storage and Processing describes information processing techniques, including those which do not appear in conventional textbooks on database systems. It focuses on the input, storage, retrieval and presentation of primarily textual information, together with auxiliary material about graphic and video data. There are chapters on text analysis as a basis for lexicography, full-text databases and information retrieval, the use of optical storage for both ASCII text and scanned document images, hypertext and multi-media systems, abstract document definition, and document formatting and imaging. The material is treated in an informal way with an emphasis on real applications and software. There are, among others, case studies from Reuters, British Airways, St. Bartholomew's Hospital, Sony, and HMSO. Relevant industry standards are discussed including ISO 9660 for CD-ROM file storage, CCITT Group4 data compression, the Standard Generalised Markup Language and Office Document Architecture, and the Postscript language. Readers will benefit from the way Susan Jones has brought together this information, in a logical sequence, to highlight the connections between related topics. This book will be of interest to second and third year undergraduates and MSc students in computer science, to B/TEC HTD final year computing and information science students either specialising in IT or taking an IT option, and to students taking courses in IT and in business computing systems.

The European Workshop on Logics in Artificial Intelligence was held at the Centre for Mathematics and Computer Science in Amsterdam, September 10-14, 1990. This volume includes the 29 papers selected and presented at the workshop together with 7 invited papers. The main themes are: - Logic programming and automated theorem proving, - Computational semantics for natural language, - Applications of non-classical logics, - Partial and dynamic logics.

Attribute grammars were introduced over twenty years ago, but they are still not as widely used as could have been hoped initially. This is particularly so in industry, despite their qualities as a specification tool. The aim of this International Workshop on Attribute Grammars and their Applications (WAGA), the first to be entirely devoted to this topic, was to show that they are still the subject of active research and now lead to important, useful and practical applications in various areas. The workshop covered all aspects of attribute grammars, with an emphasis on practical results. This volume includes the text of the three invited talks and 21 submitted papers presented at the workshop. This selection provides a wide view of the diverse research being done in the area. Topics include: - Fundamentals: efficient exhaustive and incremental at- tribute evaluation methods, parallel evaluation, space optimization, relationships with functional, logic and object-oriented programming, and systems. - Applications: compiler construction, natural language processing, and interactive program manipulation.

This volume is the proceedings of the Second Advanced School on Artificial Intelligence (EAIA '90) held in Guarda, Portugal, October 8-12, 1990. The focus of the contributions is natural language processing. Two types of subject are covered: - Linguistically motivated theories, presented at an introductory level, such as X-bar theory and head- driven phrase structure grammar, - Recent trends in formalisms which will be familiar to readers with a background in AI, such as Montague semantics and situation semantics. The topics were chosen to provide a balanced overview of the most important ideas in natural language processing today. Some of the results presented were worked out very recently, are the subject of ongoing research, and have not previously appeared in book form. This book may serve as a textbook: in fact its contents were intended as lecture notes.

We met because we both share the same views of language. Language is a living organism, produced by neural mechanisms relating in large numbers as a society. Language exists between minds, as a way of communicating between them, not as an autonomous process. The logical 'rules' seem to us an epiphe nomena .of the neural mechanism, rather than an essential component in language. This view of language has been advocated by an increasing number of workers, as the view that language is simply a collection of logical rules has had less and less success. People like Yorick Wilks have been able to show in paper after paper that almost any rule which can be devised can be shown to have exceptions. The meaning does not lie in the rules. David Powers is a teacher of computer science. Christopher Turk, like many workers who have come into the field of AI (Artificial Intelligence) was originally trained in literature. He moved into linguistics, and then into computational linguistics. In 1983 he took a sabbatical in Roger Shank's AI project in the Computer Science Department at Yale University. Like an earlier visitor to the project, John Searle from California, Christopher Turk was increasingly uneasy at the view of language which was used at Yale."

This volume contains the papers presented at the International Scientific Symposium "Natural Language and Logic" held in Hamburg in May 1989. The aim of the papers is to present and discuss latest developments in the application of logic-based meth- ods for natural language understanding. Logic-based methods have gained in importance in the field of computational linguistics as well as for representing various types of knowledge in natural language understanding systems. The volume gives an overview of recent results achieved within the LILOG project (LInguistic and LOgic methods for understanding German texts) - one of the largest research projects in the field of text understanding - as well as within related natural language understanding systems.

This book springs from a conference held in Stockholm in May June 1988 on Culture, Language and Artificial Intelligence. It assembled more than 300 researchers and practitioners in the fields of technology, philosophy, history of ideas, literature, lin guistics, social science, etc. It was an initiative from the Swedish Center for Working Life, based on the project AI-Based Systems and the Future of Language, Knowledge and Responsibility in Professions within the COST 13 programme of the European Commission. Participants in the conference, or in some cases researchers related to its aims, were chosen to contribute to this book. It was preceded by Knowledge, Skill and Artificial Intelligence (ed. B. G6ranzon and 1. Josefson, Springer-Verlag, London, 1988) and will be followed by Dialogue and Technology (ed. M. Florin and B. Goranzon, Springer-Verlag, London, 1990). The contributors' thinking in this field varies greatly; so do their styles of writing. For example: contributors have varied in their choice of 'he' or 'he/she' for the third person. No distinction is intended but chapters have been left with the original usage to avoid extensive changes. Similarly, individual contributor's preferences as to notes or references lists have been followed. We want to thank our researcher Satinder P. Gill for excellent work with summaries and indexes, and Sandi Irvine of Springer Verlag for eminent editorial work."

Dr AIvy Ray Smith Executive Vice President, Pixar The pOlyglot language of computer animation has arisen piecemeal as a collection of terms borrowed from geometry, film, video, painting, conventional animation, computer graphiCS, computer science, and publishing - in fact, from every older art or science which has anything to do with pictures and picture making. Robi Roncarelli, who has already demonstrated his foresight by formally identifying a nascent industry and addressing his Computer Animation Newsletter to it, here again makes a useful contribution to it by codifying its jargon. My pleasure in reading his dictionary comes additionally from the many historical notes sprinkled throughout and from surprise entries such as the one referring to Zimbabwe. Just as Samuel Johnson's dictionary of the English language was a major force in stabilizing the spelling of English, perhaps this one will serve a similar purpose for computer animation. Two of my pets are "color" for "colour" and "modeling" "modelling", under the rule that the shorter accepted spelling is always preferable. [Robi, are you reading this?] [Yes, AIvy!] Now I commend this book to you, whether you be a newcomer or an oldtimer.

Die 5. Osterreichische Artificial-Intelligence-Tagung setzt sich zusammen aus wissenschaftlichem Programm, Workshops und Tutorials. Der wissenschaftlich orientierte Teil des Tagungsprogramms umfasst sowohl eingeladene als auch begutachtete Vortrage zu den Themen Qualitatives Schliessen, Methodik Wissensbasierter Systeme und deren Anwendung, Logik/Deduktion, Naturlichsprachliche Systeme, Lernen und Kognition. Zum Informationsaustausch waren zusatzlich Workshops zur Weiterbildung vorgesehen. Besonders das Thema "Philosophie und KI" demonstrierte das allgemeine Interesse. Dies soll mit Beitragen dokumentiert werden, die einen Uberblick uber Beruhrungspunkte der KI mit philosophischen Stromungen bieten und auch den Einfluss der KI als Teil der Informatik auf das philosophische Weltbild verdeutlichen. Ebenfalls reprasentative Beitrage wurden zu den Workshops "Konnektionismus", "Qualitatives Schliessen" und "Begriffsbildung/-modellierung" ausgewahlt.

In der aktuellen Forschung wird zunehmend deutlich, dass fur "intelligente Systeme" die Fahigkeit, naturliche Sprachen zu verstehen, entscheidend ist und dass die theoretische Grundlegung eine wesentliche Voraussetzung fur das maschinelle Sprachverstehen darstellt. In dem Band werden vor allem die grammatikalischen und mathematischen Grundlagen der Sprachverstehenssysteme behandelt. Ausserdem werden auch kommunikationstheoretische und psycholinguistische Aspekte der Computersimulation angesprochen und die praktische Umsetzung theoretischer Resultate in Form von Grammatik-Werkzeugen. Das Buch soll die Aufmerksamkeit auf die theoretischen Aspekte der Computerlinguistik lenken und damit im deutschen Sprachraum eine Entwicklung fordern, die in der amerikanischen Wissenschaft schon vor einigen Jahren eingesetzt hat.

This series will include monographs and collections of studies devoted to the investigation and exploration of knowledge, information and data-processing systems of all kinds, no matter whether human, (other) animal or machine. Its scope is intended to span the full range of interests from classical problems in the philosophy of mind and phi losophical psychology through issues in cognitive psychology and socio biology (concerning the mental capabilities of other species) to ideas related to artificial intelligence and computer science. While primary emphasis will be placed upon theoretical, conceptual and epistemologi cal aspects of these problems and domains, empirical, experimental and methodological studies will also appear from time to time. Among the most challenging and difficult projects within the scope of artificial intelligence is the development and implementation of com puter programs suitable for processing natural language. Our purpose in compiling the present volume has been to contribute to the foundations of this enterprise by bringing together classic papers devoted to crucial problems involved in understanding natural language, which range from issues of formal syntax and logical form to those of possible-worlds and situation semantics. The book begins with a comprehensive introduc tion composed by Jack Kulas, the senior editor of this work, which pro vides a systematic orientation to this complex field, and ends with a selected bibliography intended to promote further research. If our efforts assist others in dealing with these problems, they will have been worthwhile. J. H. F."

Dieser Band ist der Bericht von einer Tagung zum Thema Verarbeitung natA1/4rlicher Sprache am Computer. Er enthAlt Lang- und KurzbeitrAge fA1/4hrender Wissenschaftler aus dem deutschsprachigen Raum sowie aus den USA. Alle Teilbereiche der Sprachverarbeitung wie Morphologie, Parsing, semantische Analyse und Verarbeitung gesprochener Sprache werden abgedeckt. Das Ziel der Tagung war eine Darstellung des Themas, die die Verarbeitung der deutschen Sprache in den Mittelpunkt rA1/4ckt. So behandeln die BeitrAge einige speziell fA1/4r das Deutsche entwickelte Systeme, sowie Adaptierungen von fA1/4r das Englische bewAhrten Formalismen fA1/4r die Anwendung auf das Deutsche. Dadurch liefert dieses Buch zum ersten Mal eine kompakte Zusammenstellung der neuesten Forschungsergebnisse unter diesem speziellen Gesichtspunkt.

Ever since Chomsky laid the framework for a mathematically formal theory of syntax, two classes of formal models have held wide appeal. The finite state model offered simplicity. At the opposite extreme numerous very powerful models, most notable transformational grammar, offered generality. As soon as this mathematical framework was laid, devastating arguments were given by Chomsky and others indicating that the finite state model was woefully inadequate for the syntax of natural language. In response, the completely general transformational grammar model was advanced as a suitable vehicle for capturing the description of natural language syntax. While transformational grammar seems likely to be adequate to the task, many researchers have advanced the argument that it is "too adequate. " A now classic result of Peters and Ritchie shows that the model of transformational grammar given in Chomsky's Aspects IJ is powerful indeed. So powerful as to allow it to describe any recursively enumerable set. In other words it can describe the syntax of any language that is describable by any algorithmic process whatsoever. This situation led many researchers to reasses the claim that natural languages are included in the class of transformational grammar languages. The conclu sion that many reached is that the claim is void of content, since, in their view, it says little more than that natural language syntax is doable algo rithmically and, in the framework of modern linguistics, psychology or neuroscience, that is axiomatic."

Originally published in 1992, when connectionist natural language processing (CNLP) was a new and burgeoning research area, this book represented a timely assessment of the state of the art in the field. It includes contributions from some of the best known researchers in CNLP and covers a wide range of topics. The book comprises four main sections dealing with connectionist approaches to semantics, syntax, the debate on representational adequacy, and connectionist models of psycholinguistic processes. The semantics and syntax sections deal with a variety of approaches to issues in these traditional linguistic domains, covering the spectrum from pure connectionist approaches to hybrid models employing a mixture of connectionist and classical AI techniques. The debate on the fundamental suitability of connectionist architectures for dealing with natural language processing is the focus of the section on representational adequacy. The chapters in this section represent a range of positions on the issue, from the view that connectionist models are intrinsically unsuitable for all but the associationistic aspects of natural language, to the other extreme which holds that the classical conception of representation can be dispensed with altogether. The final section of the book focuses on the application of connectionist models to the study of psycholinguistic processes. This section is perhaps the most varied, covering topics from speech perception and speech production, to attentional deficits in reading. An introduction is provided at the beginning of each section which highlights the main issues relating to the section topic and puts the constituent chapters into a wider context.

This book is for developers who are looking for an overview of basic concepts in Natural Language Processing. It casts a wide net of techniques to help developers who have a range of technical backgrounds. Numerous code samples and listings are included to support myriad topics. The first chapter shows you various details of managing data that are relevant for NLP. The next pair of chapters contain NLP concepts, followed by another pair of chapters with Python code samples to illustrate those NLP concepts. Chapter 6 explores applications, e.g., sentiment analysis, recommender systems, COVID-19 analysis, spam detection, and a short discussion regarding chatbots. The final chapter presents the Transformer architecture, BERT-based models, and the GPT family of models, all of which were developed during the past three years and considered SOTA ("state of the art"). The appendices contain introductory material (including Python code samples) on regular expressions and probability/statistical concepts. Companion files with source code and figures are included. FEATURES: Covers extensive topics related to natural language processing Includes separate appendices on regular expressions and probability/statistics Features companion files with source code and figures from the book.