Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 3 No. 14
Machine Learning List: Vol. 3 No. 14
Sunday, August 25, 1991
Contents:
CFP - Special Series on Genetic Algorithms in IEEE Expert
CFP: INTEGRATING LEARNING CAPABILITIES INTO INFORMATION SYSTEMS
Lexical Acquistion:
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 FTP'd from ics.uci.edu in /usr2/spool/ftp/pub/ml-list/V<X>/<N> or N.Z
where X and N are the volume and number of the issue; ID & password: anonymous
------------------------------
Date: Thu, 8 Aug 91 07:26:40 EDT
From: gref@aic.nrl.navy.MIL
Subject: CFP - Special Series on Genetic Algorithms in IEEE Expert
IEEE Expert
Special Series on
Genetic Algorithms and Their Applications
IEEE Expert announces a Special Series on Genetic Algorithms and Their
Application, edited by John Grefenstette. A Special Series is a a
collection of articles united by a theme that will run over several
issues. Current Special Series in IEEE Expert include object-oriented
programming in AI, AI applications in process systems, functional
modeling of devices, machine learning applications, and connectionist
applications.
For the Special Series on Genetic Algorithms and Their Application,
articles are sought on the following topics: characterizations of
appropriate problems for genetic algorithms, comparisons with other
algorithms for search and learning, implementation issues,
representation issues, parallel processing with genetic algorithms, and
applications.
IEEE Expert is a magazine of applied AI, not a transactions or a
journal. The Magazine is a bridge between the research community and
the user community. It aims to publish original articles that transfer
to the user community ideas and tools that come out of research and
development. Clear, not overly formal, writing is essential. Its
readers are users, developers, managers, researchers, and purchasers who
are interest in databases, expert systems, and artificial intelligence,
with particular emphasis on applications. They want to learn about the
tools, techniques, concepts, aids, and systems that have potential for
real-world applications. Conceptual or theoretical articles are
welcome, provided they serve the above function of clarifying and
presenting ideas of potential importance to applications.
Submissions should be written according the IEEE Expert style. The
final articles should be about 8-9 printed pages, with about 10-12
references. All articles submitted will be carefully reviewed.
Articles accepted on technical grounds are subject to copy editing by
the Managing Editor's staff for clarity and expressiveness. Authors are
asked to submit six copies (hard-copy only) of their article by October
1, 1991 to the Guest Editor:
John J. Grefenstette
Navy Center for Applied Research in AI
Code 5514
Naval Research Laboratory
Washington, DC 20375-5000
USA
email: gref@aic.nrl.navy.mil
------------------------------
Date: Mon, 19 Aug 91 22:16:46 -0500
From: "Andrew B. Whinston" <abw@emx.utexas.edu>
Subject: CFP: INTEGRATING LEARNING CAPABILITIES INTO INFORMATION SYSTEMS
CALL FOR PAPERS
INTEGRATING LEARNING CAPABILITIES INTO
INFORMATION SYSTEMS
Research papers on integrating learning capabilities into information systems
are solicited for a special focused section to be published in the
Journal of Management Information Systems.
DESCRIPTION
Recently much attention has been focused on developing intelligent
information systems. One major component that can make a system
"intelligent" is its automatic learning capability. A learning system
can adapt itself to new environments and improve its performance with
minimum intervention from the developer. Learning capabilities can
help the system improve its data, model, inference engine, knowledge
base, and user interface components, and make the system easy to use.
Therefore, it is interesting to investigate the integration of learning
capabilities into various types of information systems. In addition,
many different learning techniques, including rule induction,
explanation-based learning, learning by analogy, neural networks,
and genetic algorithms, have been developed in the past decade.
It is also interesting to examine how these techniques can be used
to improve the performance of information systems and how they compare
to each other.
Papers appropriate for publication should address issues related to the
integration of learning capabilities into information systems.
They must deal with a system within the general framework of MIS.
The authors should clearly describe the target of the learning component,
the benefits and limitations of integrating learning capabilities,
technical information of the proposed learning technique, and any
empirical results from using the technique. All papers will be blindly
reviewed based on their creativity, relevance to MIS, technical accuracy,
and quality of presentation.
IMPORTANT DATES
One-page abstract due October 30, 1991
Full paper due (5 copies) December 15, 1991
Notification of review results March 31, 1992
Final paper due June 31, 1992
SUBMISSION
Interested contributors should contact:
Professor Ting-Peng Liang
Krannert Graduate School of Management
Purdue University
West Lafayette, IN 47907
liang@zeus.mgmt.purdue.edu
------------------------------
Date: Thu, 8 Aug 91 10:07:17 EDT
From: uri zernik <zernik@sol.crd.ge.COM>
Subject: Lexical Acquisition book
Our volume "Lexical Acquisition: Exploiting On-Line
Resources to Build a Lexicon", with Lawrence Erlbaum,
is now out.
The contents:
Part I: Lexical Senses
2. Making Sense of Lexical Acquisition Paul Jacobs
3. Lexical Acquisition and Information Retrieval Robert Krovetz
4. Using Context for Sense Preference Brian Slator
5. Tagging Word Sense In Corpus Uri Zernik
Part II: Lexical Statistics
6. Using Statistics in Lexical Analysis Kenneth Church, William Gale,
Patrick Hanks, and Donald Hindle
7. Macrocoding the Lexicon with Co-occurrence Knowledge
Frank Smadja
8. Lexical Databases and Textual Corpora: Perspectives of Integration for
a Lexical Knowledge-Base Nicoletta Calzolari
Part III: Lexical Representation
9. WordNet: A Lexical Database Organized on Psycholinguistic Principles
Richard Beckwith, Christiane Fellbaum,
Derek Gross, and George Miller
10. Admitting Impediments Sue Atkins and Beth Levin
11. Conceptual Basis of the Lexicon in Machine Translation
Bonnie Dorr
12. Lexical Acquisition through Symbol Recirculation
Michael Dyer
Part IV: Lexical Semantics
13. Acquiring a Semantic Lexicon for Natural Language Processing
Paola Velardi
14. Representing and Acquiring Metaphor-Based Polysemy
James Martin
15. Lexicons for Broad Coverage Semantics
Lisa Braden-Harder and Wlodek Zadrozny
ISBNNO: 8058-0829-9 (hard cover)
8058-1127-3 (paperback, $34.50)
------------------------------
END of ML-LIST 3.14