Information retrieval (IR) is becoming an increasingly important area as scientific, business and government organisations take up the notion of "information superhighways" and make available their full text databases for searching. Containing a selection of 35 papers taken from the 17th Annual SIGIR Conference held in Dublin, Ireland in July 1994, the book addresses basic research and provides an evaluation of information retrieval techniques in applications. Topics covered include text categorisation, indexing, user modelling, IR theory and logic, natural language processing, statistical and probabilistic models of information retrieval systems, routing, passage retrieval, and implementation issues.
This Book Aims At Helping The Reader Develop A Clear Under- Standing Of Text Retrieval Systems, Including Its Nature And Characteristics; Steps To Be Followed In Developing A Text Retrieval System; Software Packages Available For The Purpose; Guidelines For Choosing An Appropriate Software, And So On. To Make The Text Suitable For All Kinds Of Readers, Chapters And The Basics Of Database Technology, Database Management, And File Structures Appropriate For Text Retrieval Systems Have Been Provided. This Book Also Discusses The Major Features Of Library Management Systems (Lmss), The Software Packages Used For Automating Library House-Keeping Operations.The Trend Is To Developing Systems Which Can Provide The Actual Information Sought By The Use Rather Than Reference To The Information Sources Or Part Of The Text Where The Search Term Appears. Such Systems Apply Expert Systems And Natural Language Processing Techniques, And Are Called Knowledge-Based Systems (Kbss). This Book Describes Features Of These Systems And Mentions Some Of The Applications Of Kbss In Library And Information Activities.
This book constitutes the refereed proceedings of the Third European Conference on Research and Advanced Technology for Digital Libaries, ECDL'99, held in Paris, France in September 1999. The 26 revised full papers presented were carefully reviewed and selected from a total of 124 submissions. The book is divided in topical sections on image categorization and access, audio and video in digital libraries, information retrieval, user adaptation, knowledge sharing, cross language issues, case studies, and modelling, accessability and connectedness.
This volume is a presentation of all methods of legal knowledge representation from the point of view of jurisprudence as well as computer science. A new method of automatic analysis of legal texts is presented in four case studies. Law is seen as an information system with legally formalised information processes. The achieved coverage of legal knowledge in information retrieval systems has to be followed by the next step: conceptual indexing and automatic analysis of texts. Existing approaches of automatic knowledge representations do not have a proper link to the legal language in information systems. The concept-based model for semi-automatic analysis of legal texts provides this necessary connection. The knowledge base of descriptors, context-sensitive rules and meta-rules formalises properly all important passages in the text corpora for automatic analysis. Statistics and self-organising maps give assistance in knowledge acquisition. The result of the analysis is organised with automatically generated hypertext links. Four case studies show the huge potential but also some drawbacks of this approach.
This book constitutes the refereed proceedings of the 10th International Symposium on Methodologies for Intelligent Systems, ISMIS'97, held in Charlotte, NC, USA, in October 1997. The 57 revised full papers were selected from a total of 117 submissions. Also included are four invited papers. Among the topics covered are intelligent information systems, approximate reasoning, evolutionary computation, knowledge representation and integration, learning and knowledge discovery, AI-Logics, discovery systems, data mining, query processing, etc.
This volume presents state-of-the-art research from a wide area of subjects brought about by the digital convergence of computing, television, telecommunications and the World-Wide Web. It represents a unique snapshot of trends across a wide range of subjects including virtual environments; virtual reality; telepresence; human-computer interface design; interactivity; avatars; and the Internet. Both researchers and practitioners will find it an invaluable source of reference.
This book constitutes the refereed proceedings of the 11th Biennial Conference of the Canadian Society for Computational Studies of Intelligence, AI 96, held in Toronto, Ontario, Canada, in May 1996. The 35 revised full papers presented in the book were carefully selected by the program committee. Although organized by a national society, AI 96 attracted contributions and participants with a significant geographic diversity. The issues addressed in this volume cover an electic range of current AI topics with a certain emphasis on various aspects of knowledge representation, natural language processing, and learning.
The last decade has been one of dramatic progress in the field of Natural Language Processing (NLP). This hitherto largely academic discipline has found itself at the center of an information revolution ushered in by the Internet age, as demand for human-computer communication and informa tion access has exploded. Emerging applications in computer-assisted infor mation production and dissemination, automated understanding of news, understanding of spoken language, and processing of foreign languages have given impetus to research that resulted in a new generation of robust tools, systems, and commercial products. Well-positioned government research funding, particularly in the U. S. , has helped to advance the state-of-the art at an unprecedented pace, in no small measure thanks to the rigorous 1 evaluations. This volume focuses on the use of Natural Language Processing in In formation Retrieval (IR), an area of science and technology that deals with cataloging, categorization, classification, and search of large amounts of information, particularly in textual form. An outcome of an information retrieval process is usually a set of documents containing information on a given topic, and may consist of newspaper-like articles, memos, reports of any kind, entire books, as well as annotated image and sound files. Since we assume that the information is primarily encoded as text, IR is also a natural language processing problem: in order to decide if a document is relevant to a given information need, one needs to be able to understand its content.
