Bücher der Reihe Lecture Notes in Artificial Intelligence

An introductory review of uncertainty formalisms by the volume editors begins the volume. The first main part of the book introduces some of the general problems dealt with in research. The second part is devoted to case studies; each presentation in this category has a well-delineated application problem and an analyzed solution based on an uncertainty formalism. The final part reports on developments of uncertainty formalisms and supporting technology, such as automated reasoning systems, that are vital to making these formalisms applicable. The book ends with a useful subject index. There is considerable synergy between the papers presented. The representative collection of case studies and associated techniques make the volume a particularly coherent and valuable resource. It will be indispensable reading for researchers and professionals interested in the application of uncertainty formalisms as well as for newcomers to the topic.

Artificial Intelligence is one of the most fascinating and unusual areas of academic study to have emerged this century. For some, AI is a true scientific discipline, that has made important and fundamental contributions to the use of computation for our understanding of nature and phenomena of the human mind; for others, AI is the black art of computer science.Artificial Intelligence Today provides a showcase for the field of AI as it stands today. The editors invited contributions both from traditional subfields of AI, such as theorem proving, as well as from subfields that have emerged more recently, such as agents, AI and the Internet, or synthetic actors. The papers themselves are a mixture of more specialized research papers and authorative survey papers.The secondary purpose of this book is to celebrate Springer-Verlag's Lecture Notes in Artificial Intelligence series.

Information extraction (IE) is a new technology enabling relevant content to be extracted from textual information available electronically. IE essentially builds on natural language processing and computational linguistics, but it is also closely related to the well established area of information retrieval and involves learning. In concert with other promising intelligent information processing technologies like data mining, intelligent data analysis, text summarization, and information agents, IE plays a crucial role in dealing with the vast amounts of information accessible electronically, for example from the Internet. The book is based on the Second International School on Information Extraction, SCIE-99, held in Frascati near Rome, Italy in June/July 1999.

The full title of the HCM network project behind this volume is VIM: A virtual multicomputer for symbolic applications. The three strands which bound the network together were parallel systems, advanced compilation techniques andarti?cialintelligence witha commonsubstrate in the programminglanguage Lisp. The initial aim of the project was to demonstrate how the combination of these three technologies could be used to build a virtual multicomputer - an ephemeral, persistent machine of available heterogeneous computing resources - for large scale symbolic applications . The system would support a virtual processor abstraction to distribute data and tasks across the multicomputer, the actual physical composition of which may change dynamically. Our practical objective was to assist in the prototyping of dynamic distributed symbolic app- cations in arti?cial intelligence using whatever resources are available (probably networked workstations), so that the developed program could also be run on more exotic hardware without reprogramming. What we had not foreseen at the outset of the project was how agents would unify the strands at the application level, as distinct from the system level o- lined above. It was as a result of the agent in?uence that we held two workshops in May and December 1997 with the title "e;Collaboration between human and arti?cial societies"e;. The papers collected in this volume are a selection from presentations made at those two workshops. In each case the format consisted of a number of invited speakers plus presentations from the network partners.

This volume has its origins in the ?rst Learning Language in Logic (LLL) wo- shop which took place on 30 June 1999 in Bled, Slovenia immediately after the Ninth International Workshop on Inductive Logic Programming (ILP'99) and the Sixteenth International Conference on Machine Learning (ICML'99). LLL is a research area lying at the intersection of computational linguistics, machine learning, and computational logic. As such it is of interest to all those working in these three ?elds. I am pleased to say that the workshop attracted subm- sions from both the natural language processing (NLP) community and the ILP community, re?ecting the essentially multi-disciplinary nature of LLL. Eric Brill and Ray Mooney were invited speakers at the workshop and their contributions to this volume re?ect the topics of their stimulating invited talks. After the workshop authors were given the opportunity to improve their papers, the results of which are contained here. However, this volume also includes a substantial amount of two sorts of additional material. Firstly, since our central aim is to introduce LLL work to the widest possible audience, two introductory chapters have been written. Dzeroski, ? Cussens and Manandhar provide an - troduction to ILP and LLL and Thompson provides an introduction to NLP.

Sequential behavior is essential to intelligence in general and a fundamental part of human activities, ranging from reasoning to language, and from everyday skills to complex problem solving. Sequence learning is an important component of learning in many tasks and application fields: planning, reasoning, robotics natural language processing, speech recognition, adaptive control, time series prediction, financial engineering, DNA sequencing, and so on. This book presents coherently integrated chapters by leading authorities and assesses the state of the art in sequence learning by introducing essential models and algorithms and by examining a variety of applications. The book offers topical sections on sequence clustering and learning with Markov models, sequence prediction and recognition with neural networks, sequence discovery with symbolic methods, sequential decision making, biologically inspired sequence learning models.

This volume contains updated versions of the ten papers presented at the First International Workshop on Temporal, Spatial and Spatio-Temporal Data Mining (TSDM 2000) held in conjunction with the 4th European Conference on Prin- ples and Practice of Knowledge Discovery in Databases (PKDD 2000) in Lyons, France in September, 2000. The aim of the workshop was to bring together experts in the analysis of temporal and spatial data mining and knowledge discovery in temporal, spatial or spatio-temporal database systems as well as knowledge engineers and domain experts from allied disciplines. The workshop focused on research and practice of knowledge discovery from datasets containing explicit or implicit temporal, spatial or spatio-temporal information. The ten original papers in this volume represent those accepted by peer review following an international call for papers. All papers submitted were refereed by an international team of data mining researchers listed below. We would like to thank the team for their expert and useful help with this process. Following the workshop, authors were invited to amend their papers to enable the feedback received from the conference to be included in the ?nal papers appearing in this volume. A workshop report was compiled by Kathleen Hornsby which also discusses the panel session that was held.

AI 2001 is the 14th in the series of Arti cial Intelligence conferences sponsored by the Canadian Society for Computational Studies of Intelligence/Soci et e - nadienne pour l' etude de l'intelligence par ordinateur. As was the case last year too, the conference is being held in conjunction with the annual conferences of two other Canadian societies, Graphics Interface (GI 2001) and Vision Int- face (VI 2001). We believe that the overall experience will be enriched by this conjunction of conferences. This year is the \silver anniversary"e; of the conference: the rst Canadian AI conference was held in 1976 at UBC. During its lifetime, it has attracted Canadian and international papers of high quality from a variety of AI research areas. All papers submitted to the conference received at least three indep- dent reviews. Approximately one third were accepted for plenary presentation at the conference. The best paper of the conference will be invited to appear in Computational Intelligence.

The conference series Logical Aspects of Computational Linguistics (LACL) aims at providing a forum for the presentation and discussion of current research in all the formal and logical aspects of computational linguistics. The LACL initiative started with a workshop held in Nancy (France) in 1995. Selected papers from this event have appeared as a special issue of the Journal of Logic Language and Information, Volume 7(4), 1998. In 1996, LACL shifted to the format of an international conference. LACL'96 and '97 were both held in Nancy (France). The proceedings appeared as volumes 1328 and 1582 of the Springer Lecture Notes in Arti cial Intelligence. This volume contains selected papers of the third international conference on Logical Aspects of Computational Linguistics (LACL'98), held in Grenoble, France, from December 14 to 16, 1998. The conference was organized by the U- versity Pierre Mend es-France (Grenoble 2) together with LORIA (Laboratoire Lorrain d'Informatique et Applications, Nancy). On the basis of 33 submitted 4-page abstracts, the Program Committee selected 19 contributions for pres- tation. In addition to the selected papers, the program featured three invited talks, by Maarten de Rijke (ILLC, Amsterdam), Makoto Kanazawa (Chiba U- versity, Japan), and Fernando Pereira (AT&T Labs). After the conference, the contributors were invited to submit a full paper for the conference proceedings.

We are pleased to bring you this collection of papers for the Ninth International Conference on Conceptual Structures (ICCS), representing continued excellence in conceptual structures research. We have adopted the title \Broadening the Base,"e; acknowledging the importance of contributions from scholars in many research areas. The rst ICCS meetings focused primarily on Sowa's conceptual graphs; in recent years, however, the ICCS conference series has intentionally widened its scope to stimulate research across domain boundaries. We hope that this stimulation is further enhanced by ICCS 2001 continuing the long tradition of lively conferences about Conceptual Structures. We wish to express our appreciation to all the authors of submitted papers, to the general chair, to the members of the editorial board and the program committee, and to the additional reviewers for making ICCS 2001 a valuable contribution to the knowledge processing research eld. We would also like to acknowledge the leadership of Guy Mineau and Bernhard Ganter in providing a solid framework for an open and e ective reviewing process. Very special thanks go to the local organizers for making the conference possible and, furthermore, an enjoyable and inspiring event. We are grateful to the University of Alabama in Huntsville, and the University of Karlsruhe for their generous support.