Information Retrieval List Digest 190 (November 29, 1993) URL = http://hegel.lib.ncsu.edu/stacks/serials/irld/irld-190 IRLIST Digest ISSN 1064-6965 November 29, 1993 Volume X, Number 46 Issue 190 ********************************************************** I. NOTICES Special Notice: Don Walker B. Publications 1. Int'l. Journal of Applied Expert Systems: Special Issue Call for Papers on Applied Legal Knowledge Based Systems 2. Fifth Neural Network Conference Proceedings II. QUERIES B. Requests for Information 1. Dissemination of Information 2. Objective Speech Quality Measure 3. Metrics for Describing the Population of Case-Bases 4. Case Retrieval ********************************************************** I. NOTICES Special Notice Fr: Diane H. Sonnenwald Re: Don Walker Betty has informed me that Don passed away, peacefully at home, surrounded by his family last night (Friday, Nov. 26) at 10:15 pm. For the past few days, he had been failing rapidly, as some of you may know. Don has chosen to be cremated, and so there will be a memorial service for family and friends in California at a time Betty will decide on in the future. Betty wants to thank the many of you who have had Don and her in their thoughts and prayers over the past period of illness. This has given them both great strength in dealing with the trials, pain, and also joys of the past years. Your help has been appreciated. Betty has asked me to please spread the word that donations to charities be sent to the Don and Betty Walker Student Fund. You can send them Association for Computational Linguistics c/o Judith Klavans Box 105 Hastings-on-Hudson, New York 10706 Credit card payment will be accepted. Be sure to include the expiration date of your card as well as the number (Betty has warned me that many people forget the expiration date.) You will receive an acknowledgement, and Betty will be informed as well. Personal notes for Betty can be sent to: Betty Walker 36 Oak Place Bernardsville, New Jersey 07924 Please feel free to forward this message. Peace, Judith Klavens ********** I.B.1. Fr: Dan Hunter Re: Int'l. Journal of Applied Expert Systems Special Issue: Applied Legal Knowledge Based Systems Call for Papers for the special issue of The International Journal of Applied Expert Systems on Applied Legal Knowledge Based Systems Guest Editors: Daniel Hunter, University of Melbourne, Australia John Zeleznikow, La Trobe University, Australia The International Journal of Applied Expert Systems is pleased to announce a call for papers for its special issue on Applied Legal Knowledge Based Systems, to be published in 1995. There have been many papers, books and monographs published on the theoretical aspects of legal expert systems, legal information systems, and knowledge based systems within the legal domain generally. There are journals dedicated to the theoretical questions of the merger of artificial intelligence and law. There has, however, been little discussion of the commercial, useful or practical application of artificial intelligence concepts within the legal domain. In common with most newly emerging fields, theoretical concepts in artificial intelligence and law are developed in toy legal domains, which bear little relationship to the real world, and which often cannot be said to aid in the administration of justice or of legal practice. This special issue of the International Journal of Applied Expert Systems will publish practical expositions and discussions of legal knowledge based systems which are in current use or are slated for production. The papers published will not be confined to legal knowledge based systems -- much of legal practice and the administration of justice crosses interdisciplinary borders. The editors will be pleased to consider papers which examine practical systems in law which also have features in other areas, for example, finance, education, business, social work, and so on. The special issue will examine any type of knowledge based system. The editors recognise that large components of practical legal expert systems may relate to information retrieval, litigation support, and database management, to name but a few. Papers which discuss these or other concepts in the context of legal knowledge based systems will also be considered for publication. Potential topics might include: Examples of suitable domains for legal expert systems Applications of jurisprudence in building legal expert systems Methodologies for developing legal expert systems The use of conceptual modelling in building legal expert systems Large scale, commercial, legal expert systems Descriptions of the types of legal work for which these systems are relevant (eg large scale corporate practice, legal service clinics, governmental departments, etc) Defining practical legal expert system domains The role of legal information retrieval in legal expert systems Commercial applications of legal retrieval systems and, in particular, Case Based Reasoning Interfacing hypertext with legal expert systems Dealing with the knowledge acquisition bottleneck in legal expert systems Overcoming the difficulty of scalability in large scale legal information systems The two guest editors are authors of a textbook on building intelligent information systems in legal domains, to be published by Kluwer Law & Taxation Publishers in early 1994, and have many years experience in the area of expert systems in general and legal applications in particular. The deadline for submission is 31st August 1994. Three copies of each manuscript, which should comply with the journal's standard editors: Daniel Hunter Guest Editor, IJAES, The Law School, University of Melbourne, Parkville, Victoria 3052 Australia dah@rumpole.law.unimelb.edu.au and John Zeleznikow Guest Editor, IJAES, Database Research Laboratory, Applied Computing Research Institute, La Trobe University, Bundoora, Victoria 3083 Australia johnz@latcs1.lat.oz.au! ********** I.B.2. Fr: Pulin Re: Fifth Neural Network Conference Proceedings... The Proceedings of the Fifth Conference on Neural Networks and Parallel Distributed Processing at Indiana University-Purdue University at Fort Wayne, held April 9-11, 1992 are now available. They can be ordered ($9 + $1 U.S. mail cost; make checks payable to IPFW) from: Secretary, Department of Physics Indiana University Purdue University Fort Wayne FAX: (219)481-6880 email: proceedings@ipfwcvax.bitnet Voice: (219)481-6306 OR 481-6157 The following papers are included in the Proceedings of the Fifth Conference: TUTORIALS: Phil Best, Miami University, Processing of Spatial Information in the Brain * William Frederick, Indiana-Purdue University, Introduction to Fuzzy Logic * Helmut Heller and K. Schulten, University of Illinois, Parallel Distributed Computing for Molecular Dynamics: Simulation of Large Hetrogenous Systems on a Systolic Ring of Transputer * Krzysztof J. Cios, University Of Toledo, An Algorithm Which Self-Generates Neural Network Architecture - Summary of Tutorial BIOLOGICAL AND COOPERATIVE PHENOMENA OPTIMIZATION: Ljubomir T. Citkusev & Ljubomir J. Buturovic, Boston University, Non- Derivative Network for Early Vision* M.B. Khatri & P.G. Madhavan, Indiana-Purdue University, Indianapolis, ANN Simulation of the Place Cell Phenomenon Using Cue Size Ratio* J. Wu, M. Penna, P.G. Madhavan, & L. Zheng, Purdue University at Indianapolis, Cognitive Map Building and Navigation* J. Wu, C. Zhu, Michael A. Penna & S. Ochs, Purdue University at Indianapolis, Using the NADEL to Solve the Correspondence Problem* Arun Jagota, SUNY-Buffalo, On the Computational Complexity of Analyzing a Hopfield-Clique Network NETWORK ANALYSIS: M.R. Banan & K.D. Hjelmstad, University of Illinois at Urbana-Champaign, A Supervised Training Environment Based on Local Adaptation, Fuzzyness, and Simulation* Pranab K. Das II & W.C. Schieve, University of Texas at Austin, Memory in Small Hopfield Neural Networks: Fixed Points, Limit Cycles and Chaos* Arun Maskara & Andrew Noetzel, Polytechnic University, Forced Learning in Simple Recurrent Neural Networks* Samir I. Sayegh, Indiana-Purdue University, Neural Networks Sequential vs Cumulative Update: An * Expansion D.A. Brown, P.L.N. Murthy, & L. Berke, The College of Wooster, Self- Adaptation in Backpropagation Networks Through Variable Decomposition and Output Set Decomposition* Sandip Sen, University of Michigan, Noise Sensitivity in a Simple Classifier System* Xin Wang, University of Southern California, Complex Dynamics of Discrete- Time Neural Networks* Zhenni Wang and Christine di Massimo, University of Newcastle, A Procedure for Determining the Canonical Structure of Multilayer Feedforward Neural Networks* Srikanth Radhakrishnan and C, Koutsougeras, Tulane University, Pattern Classification Using the Hybrid Coulomb Energy Network APPLICATIONS: K.D. Hooks, A. Malkani, & L. C. Rabelo, Ohio University, Application of Artificial Neural Networks in Quality Control Charts* B.E. Stephens & P.G. Madhavan, Purdue University at Indianapolis, Simple Nonlinear Curve Fitting Using the Artificial Neural Network* Nasser Ansari & Janusz A. Starzyk, Ohio University, Distance Field Approach to Handwritten Character Recognition* Thomas L. Hemminger & Yoh-Han Pao, Case Western Reserve University, A Real-Time Neural-Net Computing Approach to the Detection and Classification of Underwater Acoustic Transients* Seibert L. Murphy & Samir I. Sayegh, Indiana-Purdue University, Analysis of the Classification Performance of a Back Propagation Neural Network Designed for Acoustic Screening* S. Keyvan, L. C. Rabelo, & A. Malkani, Ohio University, Nuclear Diagnostic Monitoring System Using Adaptive Resonance Theory ********************************************************** II. QUERIES II.B.1. Fr: Karl Funk Re: Dissemination of Information. Hi all, Does any one have any references for the above subject. It is for a friend who is in her final year at university and is having difficulties getting references. The project is to analyse and suggest improvements for the information systems (customer data/balances/query handling) of a bank (actully a UK Building Society) - any relevent information is gratefully received. Electronic copies of articles or ftp sites for archives, or book / paper references are greatly appreciated. Email to my reply address please (kpf@oasis.icl.co.uk). Thanks in anticipation. Karl Funk Performance Benchmarking Unit ICL Server Systems Division Opinions expressed here are mine and not necessarily those of my employer. ********** II.B.2. Fr: Stephan Re: Objective Speech Quality Measure Hello, I am working with an adaptive filter which is used to improve the quality of speech signals. I am looking for an objective quality measure which is able to predict the subjective quality of a processed speech signal, e.g. the Mean Opinion Score. This measure should be easy to implement. There are many articles about this subject but none of them describes an implementation in detail, e.g. "An Objective Measure for Predicting Subjective Quality of Speech Coders", Shihua Wang, Andrew Sekey, Allen Gersho, IEEE Journal on Selected Areas in Commu nications, June 92. Thanks for any reply to this problem. Please answer with personal email to svoss en@mee.tcd.ie Stephan ********** II.B.3. Fr: Tony Griffiths Re: Metrics for Describing the Population of Case-Bases Hi! In the current stage of my DPhil research, I'm hunting around for some metrics which I could use to distinguish between different case-bases. The current drift is to be finding properties which can discriminate between case-bases in order to, for example, choose the most effective retrieval method, or to predict what kind of decisions that case-base would to be able to inform. At the moment I'm looking at a case-base as a set of points in an N-dimensional space, by assuming that the indices used to retrieve a case can be reduced to a set of attribute-value pairs; simple examples of the kind of measure I'm looking for are the density of the case-base and the (non-)uniformity of the case-base along different dimensions. Any suggestions of specific measures that can be used to measure non-uniformity ('clumpiness'), or any other classes of measures, would be greatly appreciated. Tony Griffiths Tony@minster.york.ac.uk Dept. of Computer Science `You come of the Lord Adam and the University of York Lady Eve,' said Aslan. `And that is York YO1 5DD both honour enough to erect the head UK of the poorest beggar, and shame enough to bow the shoulders of the greatest emperor on earth. Be content.' ********** II.B.4. Fr: Ken Laws Re: Case Retrieval Hi! I've been asked an interesting question by Eileen Knabe, a law librarian in Austin. She works with a narrow-topic database of agency case law concerning workers' compensation. Her problem is to provide easy access by non-lawyers to about 2,000 decisions of 5-10 pages each. The difficulty is that the documents all use similar terms: claimant, carrier, employer, employee, course and scope of employment, horseplay, injury, disability, impairment rating, maximum medical improvement, etc. This makes it hard to narrow a keyword search to just a few documents. Eileen is providing headnotes and summaries to simplify access, but would like to know if there are other useful indexing or retrieval approaches that she should consider. Please cc any replies to her: happy954@austin.relay.ucm.org . Ken Laws Dr. Kenneth I. Laws; (415) 493-7390; laws@ai.sri.com. Ask about my weekly AI/IS/CS online news service. ********************************************************** IRLIST Digest is distributed from the University of California, Division of Library Automation, 300 Lakeside Drive, Oakland, CA. 94612-3550. Send subscription requests to: NCG@UCCMVSA.UCOP.EDU Send submissions to IRLIST to: NCG@UCCMVSA.UCOP.EDU Editorial Staff: Clifford Lynch calur@uccmvsa.ucop.edu or calur@uccmvsa.bitnet Nancy Gusack ncgur@uccmvsa.bitnet or ncgur@uccmvsa.ucop.edu Mary Engle meeur@uccmvsa.bitnet The IRLIST Archives is now set up for anonymous FTP, as well as via the LISTSERV. Using anonymous FTP via the host dla.ucop.edu, the files will be found in the directory pub/irl, stored in subdirectories by year (e.g., /pub/irl/1993). Using LISTSERV, send the message INDEX IR-L to LISTSERV@UCCVMA.BITNET. To get a specific issue listed in the Index, send the message GET IR-L LOGYYMM, where YY is the year and MM is the numeric month in which the issue was mailed, to LISTSERV@UCCVMA (Bitnet) or LISTSERV@UCCVMA.UCOP.EDU. You will receive the issues for the entire month you have requested. These files are not to be sold or used for commercial purposes. Contact Nancy Gusack or Mary Engle for more information on IRLIST. THE OPINIONS EXPRESSED IN IRLIST DO NOT REPRESENT THOSE OF THE EDITORS OR THE UNIVERSITY OF CALIFORNIA. AUTHORS ASSUME FULL RESPONSIBILITY FOR THE CONTENTS OF THEIR SUBMISSIONS TO IRLIST.