From piola@di.unito.it Thu Dec 26 03:45:54 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id DAA15471 for ; Thu, 26 Dec 1996 03:45:49 -0600 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id DAA20305 for ; Thu, 26 Dec 1996 03:45:46 -0600 (CST) Received: from (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id QAA03429; Thu, 26 Dec 1996 16:29:08 +0800 Message-Id: <199612260829.QAA03429@cs.uwa.oz.au> From: Roberto Piola To: hybrid-list@cs.ua.edu, reinforce@cs.uwa.edu.au, neuron@CATTELL.psych.upenn.edu, ml@ics.uci.edu Subject: Learning set wanted Date: Tue, 24 Dec 1996 12:37:58 +0100 (MET) Does anybody have a publicly available learning set that mixes symbolic and numeric features and that is well-suited for a first-order learner? We are building a new learning system and we would test it on some standard test bed before building our own test set. Best Regards Roberto Piola Dept. of Computer Science University of Torino, ITALY From pazzani@super-pan.ICS.UCI.EDU Fri Dec 27 16:31:36 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA27533 for ; Fri, 27 Dec 1996 16:31:30 -0600 Received: from paris.ics.uci.edu (mmdf@paris.ics.uci.edu [128.195.1.50]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id QAA02160; Fri, 27 Dec 1996 16:31:27 -0600 (CST) Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa29128; 27 Dec 96 12:05 PST To: ML-LIST:; Subject: Machine Learning List: Vol. 8, No. 21 Reply-to: ml@ics.uci.edu Date: Fri, 27 Dec 1996 11:06:06 -0800 From: Michael Pazzani Message-ID: <9612271205.aa29128@paris.ics.uci.edu> Machine Learning List: Vol. 8, No. 21 Friday, Decemeber 27, 1996 Contents: Postdoctoral Positions in Machine Learning JAIR ML-Related articles (for ML-List) Case-Based Learning: Beyond Classification of Feature Vectors (CfP) CFP: AAI SI on ILP for KDD Call for Papers - EMNLP-2 CfP GEOMED'97 Four-T-Nine-R(sm): Data Mining of Web and non-Web Bibliographic Databases EKAW-97 Call for Papers Learning set wanted WVLC-5 CALL FOR PAPERS The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues may be obtained from http://www.ics.uci.edu/AI/ML/Machine-Learning.html ---------------------------------------------------------------------- From: Ross Quinlan Subject: Postdoctoral Positions in Machine Learning Date: Fri, 20 Dec 1996 14:37:05 +1100 Postdoctoral Positions in Machine Learning University of Sydney Two research-only positions are available as follows: (a) First-Order Learning (two years, possibility of renewal for a third) (b) Computation-Intensive Machine Learning (one year) Applicants should have a recent PhD in AI or have submitted the thesis before applying. Requirements include knowledge of symbolic empirical learning techniques, excellent communication skills, and well-developed programming skills in C and/or C++. Applications for the first position close on January 15 1997. Applications for the second position will be accepted until it is filled. Salary for both positions will be in the range A$38,092 - A$40,889. For more details on the projects and/or positions, please contact quinlan@cs.su.oz.au or phone +61 2 9351 3524. ------------------------------ From: Steve Minton Subject: JAIR ML-Related articles (for ML-List) Date: Fri, 20 Dec 96 17:13:23 PST Here is a list of ML-related articles that have appeared in JAIR (since August, the last time we sent an update). JAIR's URL is http://www.cs.washington.edu/research/jair/home.html. The abstracts follow. - Litman, D.J., "Cue Phrase Classification Using Machine Learning", - Quinlan, J.R., "Learning First-Order Definitions of Functions", - de Campos, L.M., "Characterizations of Decomposable Dependency Models" - Schlimmer, J.C. and Wells, P.C., "Quantitative Results Comparing Three Intelligent Interfaces for Information Capture: A Case Study Adding Name Information into an Electronic Personal Organizer" Litman, D.J. (1996) "Cue Phrase Classification Using Machine Learning", Volume 5, pages 53-94. see http://www.cs.washington.edu/research/jair/abstracts/litman96a.html Abstract: Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is critical in natural language processing systems that exploit discourse structure, e.g., for performing tasks such as anaphora resolution and plan recognition. This paper explores the use of machine learning for classifying cue phrases as discourse or sentential. Two machine learning programs (Cgrendel and C4.5) are used to induce classification models from sets of pre-classified cue phrases and their features in text and speech. Machine learning is shown to be an effective technique for not only automating the generation of classification models, but also for improving upon previous results. When compared to manually derived classification models already in the literature, the learned models often perform with higher accuracy and contain new linguistic insights into the data. In addition, the ability to automatically construct classification models makes it easier to comparatively analyze the utility of alternative feature representations of the data. Finally, the ease of retraining makes the learning approach more scalable and flexible than manual methods. Quinlan, J.R. (1996) "Learning First-Order Definitions of Functions", Volume 5, pages 139-161. see http://www.cs.washington.edu/research/jair/abstracts/quinlan96a.html Abstract: First-order learning involves finding a clause-form definition of a relation from examples of the relation and relevant background information. In this paper, a particular first-order learning system is modified to customize it for finding definitions of functional relations. This restriction leads to faster learning times and, in some cases, to definitions that have higher predictive accuracy. Other first-order learning systems might benefit from similar specialization. de Campos, L.M. (1996) "Characterizations of Decomposable Dependency Models" (research note), Volume 5, pages 289-300. PostScript: volume5/campos96a.ps (172K) compressed, volume5/campos96a.ps.Z (67K) see http://www.cs.washington.edu/research/jair/abstracts/campos96a.html Abstract: Decomposable dependency models possess a number of interesting and useful properties. This paper presents new characterizations of decomposable models in terms of independence relationships, which are obtained by adding a single axiom to the well-known set characterizing dependency models that are isomorphic to undirected graphs. We also briefly discuss a potential application of our results to the problem of learning graphical models from data. Schlimmer, J.C. and Wells, P.C. (1996) "Quantitative Results Comparing Three Intelligent Interfaces for Information Capture: A Case Study Adding Name Information into an Electronic Personal Organizer", Volume 5, pages 329-349. see http://www.cs.washington.edu/research/jair/abstracts/schlimmer96a.html Abstract: Efficiently entering information into a computer is key to enjoying the benefits of computing. This paper describes three intelligent user interfaces: handwriting recognition, adaptive menus, and predictive fillin. In the context of adding a personUs name and address to an electronic organizer, tests show handwriting recognition is slower than typing on an on-screen, soft keyboard, while adaptive menus and predictive fillin can be twice as fast. This paper also presents strategies for applying these three interfaces to other information collection domains. ------------------------------ From: aha@aic.nrl.navy.mil Subject: Case-Based Learning: Beyond Classification of Feature Vectors (CfP) Date: Mon, 23 Dec 1996 15:53:03 -0500 (EST) Call For Papers and Participation: Case-Based Learning: Beyond Classification of Feature Vectors An ECML-97 MLNet Familiarization Workshop (26 April 1997, Prague, Czech Republic) http://nathan.gmd.de/persons/dietrich.wettschereck/ecml-ws-cfp.html http://aic.nrl.navy.mil/~aha/ecml97-wkshp/ 1. Summary The focus of this workshop is case-based learning. Machine learning research on case-based learning is typically restricted to classification using feature-vector representations. However, several other opportunities for case-based learning exist, and our workshop is dedicated to promoting these topics. We'll have a few invited speakers, paper presentations, and a poster session, but we're reserving the entire afternoon for discussion periods whose topics will be determined by participants' votes. 2. Focus Most research on case-based learning described at machine learning conferences has focussed on classifiers for cases represented as feature vectors. Yet there are several other interesting CBR/learning topics that are worth pursuing, including learning that targets the four knowledge containers outlined by Michael Richter in his invited ICCBR-95 talk (i.e., case vocabulary, retrieval knowledge, adaptation knowledge, and the cases themselves). In this framework, most previous ML research on case-based learning focussed on retrieval knowledge (e.g., modifications of similarity functions, case indexing structures), and most of these are restricted to feature-vector representations. We encourage submissions from ML and CBR researchers who focus on more innovative case-based learning tasks and/or more ambitious case representations. We are particularly interested in submissions that focus on the following or related topics: * Problem solving rather than classification: - Learning in the context of planning - Constructing arguments (e.g., legal analyses) - Using graph-structured and other ambitious case representations * The relationship between problem-solving and case-based learning: - The roles of learning in CBR - The roles of knowledge in case-based learning tasks * Understanding the roles/benefits of learning in CBR systems: - Analyzing the utility of learning for Richter's knowledge containers - Identifying characteristics of CBR approaches that make them particularly suited for specific classes of tasks (e.g., robotic control) - Mathematical/statistical analyses characterizing case-based learning not limited to feature vector representations for classification tasks - Demonstrating how conceptual clustering (and other) approaches can be used to characterize, organize, or validate case libraries * Case-based learning in the context of: - Multi-agent systems - WWW learning assistants - Data mining - Robotic controllers (simulated or hardware) - Communication: Natural and spoken language - Integrations with other learning approaches This list is not exhaustive, and any contributions on recent advances related to case-based learning (e.g., describing the implications of interesting/novel CBR applications on future research directions) will be considered. In addition to submissions describing completed research efforts, we encourage submissions describing controversial ideas and/or raising new issues related to this workshop's focus. Contributions describing minor variants of existing case-based classifiers that use feature-vector representations are not encouraged unless they involve novel/interesting applications. 3. Structure This workshop will be more discussion-oriented than a "mini-conference" workshop. Our goal is to stimulate discussion towards identifying both relevant research advances and future research opportunities. Many workshops fail in this endeavor, primarily because plans for additional discussion are dropped when presentations overrun their allotted time periods. Thus, we will split the workshop into a morning session of invited presentations, while reserving afternoon sessions for discussion periods. A subset of the submitted papers will be selected for presentation. The remaining submissions that address the workshop's goals will be presented in a poster session. The morning session will also include invited presentations by speakers who will outline research questions and opportunities concerning case-based learning. We will select the afternoon discussion topics by soliciting and voting on suggestions from the expected attendees, who will be asked to contact us by a specific date so that we can include their votes. That is, each attendee, including both those who submit papers and those who do not, will be asked to submit three suggestions on what they believe are crucial open issues concerning learning in CBR. Each three-paragraph suggestion must (1) identify the issue, (2) explain its importance, and (3) propose directions that might be usefully pursued. (In addition, attendees are also welcome to submit a position statement and suggested panelists for a panel topic.) The Organizing Committee (OC) will then filter these suggestions, selecting a subset that will be voted on by all prospective attendees (i.e., via email). The attendees' votes will establish a priority ranking, and only the highest ranking suggestions will be selected for discussion topics. For each topic, the OC will select a discussion leader, who will be asked to define the issue, motivate its need for discussion, and suggest promising directions. The leader will also direct this discussion (e.g., by forming a panel), and assign an attendee to take notes. All information on this workshop, including the selected discussion topics, will be made available at the co-chairs (mirrored) WWW pages. 4. Submission Format Submissions must be no longer than four pages; authors of submissions are encouraged to use specific LaTeX files to format their submissions (see our WWW page). Decisions on the lengths of accepted papers will be made by the organizing committee after the review process. Submissions should include a paragraph in the final section that discusses what the authors would include if their submission is accepted and more pages are available. Papers will be published in a technical report that will be distributed to the attendees. Please submit your paper contributions and your list of issues via electronic mail to: Dietrich Wettschereck GMD (German National Research Center for Computer Science) Artificial Intelligence Research Division Schloss Birlinghoven 53754 Sankt Augustin Germany +49 2241-14-2097 | 2241-14-2072 (FAX) dietrich.wettschereck@gmd.de 5. Important dates Submission deadline (for papers): 15 February 1997 Submission deadline (for discussion topics): 15 February 1997 OC will advertise selected issues: 22 February 1997 Last chance to vote for the selected issues: 1 March 1997 Acceptance notification: 8 March 1997 Accepted papers due: 1 April 1997 Workshop date: 26 April 1997 6. Organizing Committee David W. Aha, NRL, USA; Co-chair Daniel Borrajo, Univerisdad Carlos III de Madrid, Spain Karl Branting, University of Wyoming, USA Jim Hendler, University of Maryland, USA Hector Munoz-Avila, University of Kaiserslautern, Germany Francesco Ricci, IRST, Italy Jerzy Surma, University of Economics at Wroclaw, Poland Henry Tirri, University of Helsinki, Finland Dietrich Wettschereck, GMD, Germany; Co-chair ------------------------------ From: Johannes Fuernkranz Subject: CFP: AAI SI on ILP for KDD Date: Fri, 27 Dec 1996 16:28:14 +0100 1st Call For Papers Applied Artificial Intelligence Special issue on First-Order Knowledge Discovery in Databases (URL: http://www.ai.univie.ac.at/ilp_kdd/aai-si.html) Knowledge Discovery in Databases (KDD) is the non-trivial process of identifying valid, novel, potentially useful, and ultimately understandable patterns in data (Fayyad, Piatetsky-Shapiro & Smyth, 1996). Machine Learning algorithms form the core of many KDD systems and applications. However, standard inductive learning techniques are constrained to processing a single relational table, whereas many real-world databases are structured into several tables containing interrelated information. Learning algorithms that are able to use representations in first-order logic, in particular Inductive Logic Programming (ILP) algorithms, explicitly aim at exploiting structured information. Thus KDD is a fruitful research and application area for ILP. A recent MLnet Workshop, held at the ICML-96, focussed on a discussion of the potential contribution of ILP for KDD. Information on the workshop including a short summary and all accepted papers can be found at http://www.ai.univie.ac.at/ilp_kdd/. The general conclusion was that ILP can be a valuable tool for data mining, its main advantages being the expressiveness of first-order logic as a representation language and the ability of many ILP systems to use strong language biases for restricting the huge search space. ILP has a high flexibility in incorporating various forms of background knowledge, which can be invaluable for large KDD tasks. The special issue on "First-Order Knowledge Discovery in Databases" of the Applied Artificial Intelligence Journal will thus welcome papers that focus on one or more of the following topics: * Embedding ILP into the KDD process * Necessary pre- and post-processing steps for real-world applications * Interfacing ILP systems with database managers * Scalability of ILP for real-world databases * Criteria for quantifying the complexity of ILP problems * Evaluation of gain and price of ILP versus propositional learning * Non-classification learning and discovery in a first-order framework * Benefits of using background knowledge and/or strong explicit biases * Innovative real-world applications of ILP Papers on related subjects are also welcome, but a strong focus on applications and database issues is required for all submissions. Submissions Papers should be prepared according to usual standards for journal submissions. The approximate length of a manuscript should be between 8,000 to 10,000 words. Final manuscripts of accepted papers will have to be formatted according to the Instructions to Authors, which can be found in all issues of the journal. Authors have to submit four copies of their manuscripts to * Johannes Fuernkranz * Austrian Research Institute for Artificial Intelligence * Schottengasse 3 * A-1010 Vienna * AUSTRIA * juffi@ai.univie.ac.at or * Bernhard Pfahringer * Department of Computer Science * University of Waikato * Hamilton * NEW ZEALAND * bernhard@cs.waikato.ac.nz whichever is more convenient. Submission Deadline: April 30, 1997 Each paper submitted for publication will be judged by its originality, adequacy of method, significance of findings, and relevance to the special issue's subject matter. It should be as concise as possible, yet sufficiently detailed to permit critical review. Each manuscript must be accompanied by a statement that it has not been submitted or published elsewhere. The authors of accepted papers will be asked to transfer the copyright to the publisher. ------------------------------ From: David Yarowsky Subject: Call for Papers - EMNLP-2 Date: Fri, 20 Dec 96 03:28:42 EST The Association for Computational Linguistics and its Special Interest Group SIGDAT announce the Second Conference on Empirical Methods in Natural Language Processing (EMNLP-2) Preliminary Call For Papers WHEN: August 1-2, 1997 (Immediately following AAAI-97) WHERE: Brown University, Providence, Rhode Island, USA CONFERENCE DESCRIPTION: In the spirit of SIGDAT events, this conference will offer a general forum for novel research in corpus-based and statistical natural language processing. Areas of interest include (but are not limited to): - robust parsing, phrase structure analysis - part of speech tagging - term and name identification - word sense disambiguation - morphological analysis - anaphora resolution - event categorization - discourse structure identification - alignment of parallel texts and bilingual terminology - language modelling - lexicography - machine translation - spelling and grammar correction SPECIAL SESSIONS: INFORMATION EXTRACTION and INFORMATION RETRIEVAL In addition, we encourage submissions that describe and evaluate the strengths, weaknesses, and recent advances in corpus-based NLP as applied to INFORMATION EXTRACTION and INFORMATION RETRIEVAL (IR). In recent years a number of corpus-based techniques for the automatic linguistic annotation of text have been developed. How well do these techniques for lexical tagging, parsing, anaphora resolution, etc., handle the specific problems encountered in practical language processing tasks like information extraction and information retrieval? When and how do current techniques fail? What new methods have been developed to address the deficiencies of existing algorithms for these tasks or to address problems specific to information extraction? What problems still lack an adequate empirical solution? How can data-driven NLP methods be used to improve the performance of IR systems? Conversely, how can feedback from an IR system effectively inform empirical techniques for natural language understanding? PROGRAM CHAIRS: Claire Cardie Cornell University (chair) Ralph Weischedel BBN Systems and Technologies (co-chair) LOCAL ARRANGEMENTS: Eugene Charniak Brown University SPONSOR: SIGDAT (ACL's special interest group for linguistic data and corpus-based approaches to NLP) FORMAT FOR SUBMISSION: Authors should submit a full-length paper (3500-8000 words) either electronically or in hardcopy. Electronic submissions should be mailed to "cardie@cs.cornell.edu" and must either be (a) plain ascii text, (b) a single postscript file (US letter format), or (c) a LaTex file. In the latter case, please use the aclsub style file and include only .EPS (encapsulated postscript) figures. The aclsub style file is available at http://www.cs.cornell.edu/Info/People/cardie/emnlp/aclsub.sty or via ftp from ftp.cs.cornell.edu/pub/cardie/emnlp/aclsub.sty. Hardcopy submissions should be mailed to Claire Cardie (address below), and should include six (6) copies of the paper. REQUIREMENTS: Papers should describe original work. A paper accepted for presentation cannot be presented or have been presented at any other meeting. Papers submitted to other conferences will be considered, as long as this fact is clearly indicated in the submission. SCHEDULE: Submission deadline: March 3, 1997 Notification date: April 21, 1997 Camera-ready copy due: June 10, 1997 Conference dates: August 1-2, 1997 CONTACTS: Claire Cardie Ralph Weischedel Cornell University BBN Systems and Technologies Department of Computer Science 70 Fawcett Street 4142 Upson Hall Cambridge, MA 02138 Ithaca, NY 14850 USA USA cardie@cs.cornell.edu weischedel@bbn.com (607)255-9206 (617)873-3496 ------------------------------ From: Mathias Bull Subject: CfP GEOMED'97 Date: Fri, 20 Dec 1996 09:48:19 +0100 Call for Papers GEOMED '97 International Workshop on Geomedical Systems - Foundations, Systems, and Applications - Rostock, Germany, September 4-6, 1997 Motivation During the recent years many national and international (EU) projects on geomedical systems have been established. These projects mostly include the different views of geographers, epidemiologists and computer scientists and to some extent the requirements of the potential users. We consider that a workshop presenting these different views and the possible achievements of geomedical systems in the future is highly desirable. The slides offered by the CDC in the INTERNET illustrate the dramatic situation of emerging and re-emerging infectious diseases, health risks and resistant pathogens. The ProMED-Proposal (Global Program to Monitor Emerging Diseases), which was circulated for commentation last year to more than 300 experts around the world, specifies the needs and the technical demands of public health surveillance systems. These examples highlight the need of information regarding the spread of diseases, outbreaks, epidemics and distribution patterns by means of geography, time and age- or riskgroups. Monitoring systems providing those information valuable for pharmacists, the pharmaceutical industry, physicians, public health care providers, etc. can be valuable tools for any reaction and control mechanism. The current national and international information systems monitoring human and animal infectious diseases have to be improved in order to elicit the present and future challenges. Aim GEOMED '97 offers a forum for presentation and discussion of new directions and interesting work in progress in the field of geomedical systems and closely related domains such as epidemiological models. The workshop will attempt to bring together researchers on theoretical foundations of epidemiology as well as on practical requirements and experiences from the development of geomedical applications. The workshop will be organized as a combination of invited talks, paper presentations, poster sessions and panel discussions. Invited Speakers A. D. Cliff (Cambridge, United Kingdom) C. P. Farrington (London, United Kingdom) A. Flahault (Paris, France) Contribution Contributions to the workshop are welcome from the whole field of geographic medicine and geomedical systems. Possible topics include: * Foundations - foundations of geomedical systems - space-time cluster detection - epidemiological models of the spatial-temporal spread of diseases - methods for early detection of outbreak of diseases - knowledge discovery and data mining in medical data bases * Systems - geographic information systems in epidemiology - wide-area and satellite based networks for gathering epidemiological information - scientific visualisation of epidemiological data - experiences from system development * Applications and Experiences - public health surveillance systems in practice - applications for health care authorities, physicians, hospitals, industry and science The results must be unpublished and not submitted for publication elsewhere, including the proceedings of other symposia or workshops. All authors of accepted papers will be expected to sign copyright release forms. Papers should not exceed 10 pages (1 1/2 line, Roman Times 12 pt). A paper should include the title, the list of the authors, the complete addresses (e-mail if possible), and an abstract. The workshop languages is English. The program committee decides about acceptance. The abstracts of the accepted papers will be available as pre-proceedings during the workshop. The papers presented at the workshop will be published as proceedings after the workshop. Papers (3 copies) should be sent to: Prof. Dr. Dr. Gierl Medizinische Informatik und Biometrie Medizinische Fakult=E4t Universit=E4t Rostock D-18055 Rostock Germany Papers can also be submitted via email as attachment (Word, WordPerfect, ClarisWorks-files only). Send your paper to: geomed97@medizin.uni-rostock.de Time and Place The workshop will take place in Rostock from September 4 to September 6, 1997. Important Dates March 31, 97 : deadline for papers July 1, 97 : notification of acceptance October 1, 97: camera-ready versions of accepted papers Program Committee J. Appelrath (Oldenburg, Germany) A. D. Cliff (Cambridge, United Kingdom) C. P. Farrington (London, United Kingdom) S. M. Freire (Rio de Janeiro, Brazil) L. Gierl (Rostock, Germany), chair R.Thomas (Manchester, United Kingdom) H. Uphoff (Marburg, Germany) A. Valleron (Paris, France) Organization Committee A.Brauer, M. Bull (chair), G. Kundt, R. Schmidt (Rostock, Germany) ------------------------------ From: Gerry McKiernan Subject: Four-T-Nine-R(sm): Data Mining of Web and non-Web Bibliographic Databases Date: Fri, 20 Dec 96 14:07:43 CST Four-T-Nine-R(sm) Data Mining of Web and non-Web Bibliographic Databases For a planned review and clearinghouse, I am interested in learning of projects, research, products and services that have applied Data Mining technologies to Web or non-Web _bibliographic_ data bases or datasets. I am particularly interested in the application to MARC data records. At this time I am _not_ interested in other applications of Data Mining. There are a number of excellent Web resources available to those who desire additional information about Data Mining. One of the best is KD Mine at URL: http://info.gte.com/~kdd/index.html Relevant efforts will be profiled in a new clearinghouse entitled Four-T-Nine-R(sm) at the following URL: http://www.public.iastate.edu/~CYBERSTACKS/4T9R.htm As always, any and all suggestions, reactions or critiques are most welcome. Regards, Gerry McKiernan Curator, CyberStacks(sm) Iowa State University Ames IA 50011 gerrymck@iastate.edu ------------------------------ From: Enric Plaza i Cervera Date: Fri, 20 Dec 1996 16:27:53 +0200 Subject: EKAW-97 Call for Papers EKAW-97 First Call for Papers 10th European Workshop on Knowledge Acquisition, Modeling, and Management October 15 - 18, 1997 Sant Feliu de Guixols, Catalonia (Spain) http://www.acia.org/ekaw The EKAW, together with the Banff KAW and the PKAW, has expanded the workshop scope and has become the European Workshop on Knowledge Acquisition, Modeling, and Management. The EKAW acronym and series number (currently the tenth) are maintained. The EKAW is concerned with all aspects of eliciting, acquiring, modeling and managing knowledge, and with their role in the construction of knowledge-intensive systems. Papers are invited on relevant topics, including but not restricted to: * Languages and frameworks for knowledge acquisition, modeling, and management * Tools and techniques for knowledge acquisition, modeling, and management * Acquiring knowledge through machine learning, data-mining and knowledge discovery in databases. * Knowledge acquisition and management for enterprise modeling and corporate memories. * Methods and techniques for reuse of knowledge and knowledge models, in particular related to the construction, maintenance and use of supporting libraries * Knowledge acquisition, modeling, and management over the Internet. * Agent-oriented approaches to knowledge acquisition, modeling, and management. * Evaluations of knowledge acquisition, modeling, and management techniques, tools and methods. Workshop attendance will be limited to 40 participants, one author for each paper accepted. The workshop will last 3.5 days and will consist of plenary sessions, invited talks, and working groups on selected issues. Authors are invited to formulate an issue that would be useful to discuss. Software demonstrations related to presented papers are also encouraged. ________________________ Important dates ________________________ 15 April 1997 Submission deadline 3 June 1997 Notification of acceptance 15 July 1997 Camera ready copy and author registration due 15-18 October 1997 Workshop ______________________ Submission Procedure ______________________ Authors should submit both a full paper and an "electronic title page". Full papers may be submitted in either of two ways: 1) Electronically, as a UNIX-printable postscript file, plus one hard copy. Papers should be copied by anonymous FTP to . This is the preferred mode of submission. 2) As hard copy only, sending five copies. Authors submitting electronically should check whether the generated postscript file prints well on a Unix platform, before sending it. Electronic submissions are due no later than April 15. They should also mail a single hard copy of the electronic submission as soon as possible after the electronic submission. Full instructions for electronic submissions will be available at http://www.acia.org/ekaw by January 15, 1997. Authors submitting only hard copies should send all five copies to the address below to arrive on or before April 15. Double-sided copies are strongly encouraged. In addition, authors should submit an electronic version of their title pages by April 15 to . Final instructions for electronic title pages will be available at http://www.acia.org/ekaw by January 15, 1997. ________________________ Submission Address ________________________ EKAW-97 IIIA - Artificial Intelligence Research Institute (CSIC) Campus UAB, 08193 Bellaterra, Catalonia (Spain) ________________________ Submission Format ________________________ Submitted papers should begin with a cover page containing paper title, authors' names, affiliations, postal addresses, electronic mail addresses, telephone and fax numbers for all authors, and a brief abstract. The cover page should also specify whether the submission is to be reviewed as a research paper or as an application paper. Unless the title page designates another contact person, all correspondence will be sent to the first author. Submissions should be in a 12-point font on 8.5" x 11" or A4 paper with at least 1 inch margins on all sides. Submissions should be at most 20 pages long, including cover page, figures and references. Program Committee Co-chairs Enric Plaza Richard Benjamins IIIA - Artificial Intelligence Research Institute (CSIC) Campus UAB, 08193 Bellaterra, Catalonia (Spain) Fax: +34-3-580 96 61 Phone: +34-3-580 95 70 International Program Committee Thomas R. ADDIS, University of Portsmouth (GB) Hans AKKERMANS, University of Twente (NL) Klaus-Dieter ALTHOFF, University of Kaiserslautern (G) Nathalie AUSSENAC, IRIT- CNRS, Toulouse (F) Bill BIRMINGHAM, University of Michigan (USA) John BOOSE, Boeing Comp. Services, Seattle (USA) Guy BOY, EURISCO, Toulouse (F) Jeffrey BRADSHAW, Boeing Comp. Services, Seattle (USA) I. BRATKO, University of Ljubljana, Ljubjljana (Yu) B. CHANDRASEKARAN, Ohio Univ., Columbus (USA) William CLANCEY, Inst. for Res. on Learning (USA) John DEBENHAM, Univ. of Technology, Sydney (Aus) Michael FREILING, Tektronix Inc. (USA) Brian GAINES, University of Calgary, Calgary (CA) Jean-Gabriel GANASCIA, LAFORIA-Univ. Paris VI (F) Yves KODRATOFF, LRI - Univ. Paris Sud, Orsay (F) Marc LINSTER, Digital Equipment Corp. (USA) John Mc DERMOTT, Digital Equipement Corp. (USA) Ryszard MICHALSKI, George Mason University (USA) Riichiro MIZOGUSHI, Kyoto University, Kyoto (Jap) Katharina MORIK, University of Dortmund (G) Hiroshi MOTODA, Osaka University. (Jap) Mark MUSEN, Stanford University (USA) Bruce PORTER, Univ. Of Texas, Austin (USA) Ross QUINLAN, Sydney University, Sidney (Australia) Alain RAPPAPORT, Neuron Data (USA) Franz SCHMALHOFER, DFKI, Kaiserslautern (G) Guus SCHREIBER, Univ. of Amsterdam, Amsterdam (NL) Nigel SHADBOLT, Univ. of Nottingham (GB) Mildred SHAW, Univ. of Calgary, Calgary (CA) Ingeborg SOLVBERG, Trondheim (N) Luc STEELS, Free University of Brussels (B) Hirokazu TAKI, Inst. for New Gen. Computer Tech. (Jap) Walter VAN DE VELDE, Free University of Brussels (B) Hans VOSS, GMD, Sankt Augustin (G) Masanobu WATANABE, NEC Corporation (Jap) Bob WIELINGA, Univ. of Amsterdam, Amsterdam (NL) Sponsors EKAW-97 is sponsored by the Catalan Association for Artificial Intelligence (ACIA), and the European Network of Excellence in Machine Learning (MLnet). ------------------------------ From: Roberto Piola Subject: Learning set wanted Date: Tue, 24 Dec 1996 12:37:58 +0100 (MET) Does anybody have a publicly available learning set that mixes symbolic and numeric features and that is well-suited for a first-order learner? We are building a new learning system and we would test it on some standard test bed before building our own test set. Best Regards Roberto Piola Dept. of Computer Science University of Torino, ITALY ------------------------------ From: "Joe F. Zhou" Subject: WVLC-5 CALL FOR PAPERS Date: Fri, 27 Dec 96 10:23:56 EST The Association for Computational Linguistics (ACL) and its special interest group for linguistic data and corpus-based approaches to NLP (SIGDAT) are organizing the FIFTH WORKSHOP ON VERY LARGE CORPORA (WVLC-5) WHEN: August 18-20, 1997 WHERE: Tsinghua University, Beijing, China (August 18, 1997) Hong Kong University of Science and Technology (August 20, 1997) WVLC5 will immediately precede ROCLING '97 (Aug 22-24, Taiwan) and IJCAI '97 (Aug 24-29, Nagoya, Japan). This workshop will take place in two consecutive sessions sharing a common program committee and proceedings. Authors may specify at which session(s) they wish to present their papers. SPONSORED BY: The Association for Computational Linguistics (ACL) LEXIS-NEXIS, a division of Reed Elsevier Inc. WORKSHOP DESCRIPTION: This workshop, like preceding ones in the series, will offer a general international forum for the presentation of new advances and applications in the area of large scale, corpus-based natural language processing. The fifth workshop will focus on the theme of: Innovative and practical uses of large corpora in real-world applications Gigabytes and terabytes of on-line unrestricted natural language text have become commonplace today. How are these resources actually being used in commercial as well as research applications? What robust and efficient techniques exist for analyzing and organizing these resources? The workshop encourages contributions that demonstrate innovative applications of corpus-based NLP to problems of practical commercial importance. The theme will provide an organizing structure to the workshop, and offer a focus for discussion and debate between academic researchers and industrial practitioners. We also expect and will welcome a diverse set of submissions in all areas of statistical and corpus-based NLP, including (but not limited to) Text Analysis Techniques: - part of speech tagging - term and name identification - morphological analysis - robust parsing - alignment of parallel texts and bilingual terminology - sense disambiguation - anaphora resolution - event categorization - discourse structure Applications: - information retrieval - information extraction - text categorization and summarization - lexicography - machine translation - spelling and grammar correction - recognition: speech, OCR, handwriting, etc. PROGRAM CHAIRS: Huang Changning - Tsinghua University (Beijing, China) Ken Church - AT&T Laboratories (Murray Hill, NJ, USA) Joe Zhou - LEXIS-NEXIS (Dayton, OH, USA) FORMAT FOR SUBMISSION: Authors should submit a full-length paper (3500-8000 words), either electronically or in hard copy. Electronic submissions should be mailed to "WVLC5@lexis-nexis.com" and must either be (a) plain ascii text, (b) a single postscript file, or (c) a single latex file following the ACL-97 stylesheet (no separate figures or .bib files). Hard copy submissions should be mailed to Ken Church (address below), and should include four (4) copies of the paper. REQUIREMENTS: Papers should describe original work. A paper accepted for presentation cannot be presented or have been presented at any other meeting. Papers submitted to other conferences will be considered, as long as this fact is clearly indicated in the submission. SCHEDULE: Submission Deadline: April 7, 1997 Notification Date: May 20, 1997 Camera ready copy due: July 1, 1997 CONTACT: Ken Church Joe Zhou Room 2B-421 LEXIS-NEXIS, a Division of Reed Elsevier AT&T Laboratories 9555 Springboro Pike Murray Hill, NJ 07974 USA Dayton, OH 45342 USA e-mail: kwc@research.att.com email: joez@lexis-nexis.com ------------------------------ From: tibs@utstat.toronto.edu Subject: course announcement Date: Thu, 19 Dec 96 22:49 EST MODERN REGRESSION AND CLASSIFICATION Waikiki, Hawaii: February 17-18, 1997 ************************************************* A two-day course on widely applicable statistical methods for modeling and prediction, featuring Professor Trevor Hastie and Professor Robert Tibshirani Stanford University University of Toronto This course was offered and enthusiastically attended at five different locations in the USA in 1996. This two day course covers modern tools for statistical prediction and classification. We start from square one, with a review of linear techniques for regression and classification, and then take attendees through a tour of: o Flexible regression techniques o Classification and regression trees o Neural networks o Projection pursuit regression o Nearest Neighbor methods o Learning vector quantization o Wavelets o Bootstrap and cross-validation We will also illustrate software tools for implementing the methods. Our objective is to provide attendees with the background and knowledge necessary to apply these modern tools to solve their own real-world problems. The course is geared for: o Statisticians o Financial analysts o Industrial managers o Medical and Quantitative researchers o Scientists o others interested in prediction and classification Attendees should have an undergraduate degree in a quantitative field, or have knowledge and experience working in such a field. PRICE: $750 per attendee if received by January 15, 1997. Full time registered students receive a 40% discount. Attendance is limited to the first 60 applicants, so sign up soon! These courses fill up quickly. TO REGISTER: Fill in and return the form appended. For more details on the course and the instructors: o point your web browser to: http://stat.stanford.edu/~trevor/mrc.html OR send a request by o FAX to Prof. T. Hastie at (415) 326-0854, OR o email to trevor@stat.stanford.edu Please print, and fill in the hard copy to return by mail or FAX REGISTRATION FORM Modern Regression and Classification Monday, February 17 and Tuesday, February 18, 1997. Hilton Hawaiian Village, Waikiki Beach, Honolulu, Hawaii. Name ___________________________________________________ Last First Middle Firm or Institution ______________________________________ Standard Registration ____ Student Registration ____ Mailing Address (for receipt) _________________________ __________________________________________________________ __________________________________________________________ __________________________________________________________ Country Phone FAX __________________________________________________________ email address __________________________________________ _______________ Credit card # (if payment by credit card) Expiration Date (Lunch preference - tick as appropriate): ___ Vegetarian ___ Non-Vegetarian Fee payment can be made by MONEY ORDER , PERSONAL CHECK, or CREDIT CARD (Mastercard or Visa.) For checks and money orders: all amounts are given in US dollar figures. Make fee payable to Prof. T. Hastie. Mail it, together with this completed Registration Form to: Prof. T. Hastie 538 Campus Drive Stanford CA 94305 USA For payment by credit card, include credit card details above, and mail to above address, or else FAX form to 415-326-0854 For further information, contact: Trevor Hastie Stanford University Tel. or FAX: 415-326-0854 e-mail: trevor@stat.stanford.edu. http://stat.stanford.edu/~trevor/mrc.html REGISTRATION FEE Standard Registration: U.S. $750 ($950 after Jan 15, 1997) Student Registration: U.S. $450 ($530 after Jan 15, 1997) Student registrations - include copy of student ID. - Cancellation policy: No fee if cancellation before Jan 15, 1997. - Cancellation fee after January 15 but before Feb 12, 1997: $100. - Refund at discretion of organizers if cancellation after Feb 12, 1997. - Registration fee includes course materials, coffee breaks, and lunches - On-site Registration is possible if course is not fully booked, at late fee. Trevor Hastie trevor@stat.stanford.edu Phone: 415-725-2231 Fax: 415-725-8977 ftp://stat.stanford.edu/pub/hastie/ http://stat.stanford.edu/~trevor paper: Statistics Department, Stanford University, CA94305 office: Margaret Jacks Hall, rm 362 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Rob Tibshirani, Dept of Preventive Med & Biostats, and Dept of Statistics Univ of Toronto, Toronto, Canada M5S 1A8. Phone: 416-978-4642 (PMB), 416-978-0673 (stats). FAX: 416 978-8299 computer fax 416-978-1525 (please call or email me to inform) tibs@utstat.toronto.edu. ftp: //utstat.toronto.edu/pub/tibs http://www.utstat.toronto.edu/~tibs