Date: Thu, 5 Jul 2001 23:34:22 +0100 (BST)
From: Ayse S Goker-Arslan <[log in to unmask]>
Reply-To: Ayse S Goker-Arslan <[log in to unmask]>
Subject: Re: call for participation
Appologies for cross-posting.
Please forward to collegues who may be interested.
--------------
Call for Participation & Schedule
UM2001 8th International Conference on User Modeling
Workshop on User Modeling, Machine Learning and Information
Retrieval
(http://www.scms.rgu.ac.uk/um2001-ws)
July 13-14, 2001 - Sonthofen, Germany
Please find below the Overview, Schedule and Registration details for the
workshop.
OVERVIEW
The rapid evolution of Internet services has led to a constantly
increasing
number of Web sites, and to an increase in the available information.
Thus, the
main challenge is to support Web users in order to facilitate
navigation through Web sites and to improve searching among the extremely
large
Web repository.
Usually, users have to decide themselves which sequence of actions must be
performed to solve a given task. Complex search queries, for example, must
be
constructed step by step. The complexity of today's
services could be lowered by means of a "pro-active" support or advice
from the
system. To meet these conditions the interaction must convey precise and
relevant information, and address the personal background
of the individual user.
Web search engines use the typical information retrieval paradigm of a few
words
to represent the user need, and then match against very large numbers of
documents, in particular, web pages. The results are often
very mixed. This is partially because of the very poor user model. Two
people
may have very different needs but use the same two word query.
The system should be able to adapt to individual users, to learn about
their
preferences and attitudes during the interaction (to construct a user
profile),
and memorize them for later use. Moreover, these user profiles
could represent a starting point for the creation of user communities
based on
shared interests or goals. Thus we have two important questions: how can
we
acquire a good user model, and how can we exploit that
model?
Machine Learning techniques, that extract permanent features of a given
user
from the dialogue, represent a very promising solution: i) they have been
successful in cases where large data sets were available by
providing tools for retrieval and filtering of useful information; ii)
they have
been applied to the definition of models of users interacting with an
information system.
Information retrieval techniques then need to be augmented to exploit the
more
sophisticated model. This can be done by constructing an answer out of a
set of
targeted information retrieval (IR) queries, or by more
sophisticated use of IR and database approaches.
SCHEDULE
13 July, 2001 (Friday)
Joint Session with ML4UM Workshop: Applications (14:00 - 16:00)
Chair: Ralph Schäfer
14:00 - 14:30
Automatic Induction of Rules for e-mail Classification
(J. Kay and E. McCreath)
14:30 - 15:00
Inducing Content Based User Models with Inductive Logic
Programming Techniques
(M. Müller)
15:00 - 15:30
An Adaptive Web Site for the UM 2001 Conference
(Eric Schwarzkopf)
15:30 - 16:00
Discussion about the whole session topic
Please see http://www.dfki.de/~rafer/um01-ml4um-ws/ for details on other
papers in the ML4UM Workshop in the morning session on 13 July, 2001.
First Session for ML-IR-UM Workshop (16:30 - 17:40)
16:30 - 17:00
Opening to ML-IR-UM Workshop:
- Aims/objectives of Workshop
- Participants introduce each other
17:00 - 17:30
Intelligent Information Triage
(Sofus A. Macskassy, Haym Hirsh, Foster Provost, Ramesh
Sankaranarayanan,
Vasant Dhar)
14 July, 2001 (Saturday)
Second Session for ML-IR-UM Workshop (09:00 - 13:00)
09:00 - 09:30
A Task-Model for Text Corpus Analysis in Knowledge Management
(Andreas Becks, Christian Seeling)
09:30 - 10:00
Toward Understanding WH-Questions: A Statistical Analysis
(Ingrid Zukerman and Eric Horvitz)
10:00 - 10:30
Using Linear Classifiers in the Integration of User Modeling and Text
Content Analysis in the Personalization of a Web-based Spanish News
Service
(Alberto Díaz Esteban, Manuel J. Maña López, Manuel de Buenaga
Rodríguez,
Jose María Gómez Hidalgo, Pablo Gervás Gómez-Navarro)
10:30 - 11:00
A Web Document Personalization User Model and System
(Chien Chin Chen, Meng Chang Chen, Yeali Sun)
Break (11:00 - 11:30)
11:30 - 12:30
Discussion
12:30 - 13:00
Summing Up
REGISTRATION - Hotel Reservation
All workshop participants are required to also register with the main
UM2001
conference.
Visit the site of the 8th International Conference on User Modeling
(http://www.dfki.de/um2001) for further details about Registration and
Hotel
Reservation.
ORGANIZERS
Ayse Goker, Robert Gordon University, Scotland, UK ([log in to unmask])
Fabio Abbattista, Università di Bari, Italy ([log in to unmask])
Ross Wilkinson, CSIRO, Australia ([log in to unmask])
Giovanni Semeraro, Università di Bari, Italy ([log in to unmask])
--------------------
|