Appel: MT Summit VII Workshop

[Pierre Zweigenbaum]

Date: Tue, 30 Mar 1999 20:55:33 +0900
From: "Megumi Kiya" <aamt0002 at infotokyo.ne.jp>
Message-Id: <01be7aa4$376bf600$0100007f at localhost>


----------------------------------------------------------------
Workshop on Machine Translation for Cross Language Information Retrieval
----------------------------------------------------------------

 Introduction

The goal of this workshop is to explore the role of MT in the context of
CLIR.
Undoubtedly searching, extracting and summarising information from the Web
is a major challenge demanding multilingual solutions. Despite the fact that
currently much  textual WWW information is in English, the situation is
radically
changing. In addition, there is an increased amount of users who would
prefer to
use sites and/or query  in their native language.  There are different
strategies
for CLIR involving document translation, query translation,  use of
dictionaries.
The adoption of a  strategy depends on the user profile, the level of user
interaction  intended  in the search process, the targeted use of the
documents
retrieved and the availability of linguistic resources, among others.

We invite papers on topics which link advances in Machine Translation  or
related technologies  to CLIR. Are existing MT solutions sufficient for the
information access demands of today?  What type of MT linguistic analysis
would be useful for CLIR?  How can we identify the proper translations of
query terms? How can we improve on existing techniques to improve precision
and recall? A non-exhaustive list, which should serve as a starting point,
follows:

* Issues in query translation and query expansion
* Alignment techniques for dictionary building
* Level and type of linguistic MT analysis for CLIR (shallow, chunking,
...)
* Type of  multilingual resources (corpora, dictionaries, terminologies)
used in CLIR
* Role of terminology and ontologies in CLIR
* Translation Memories in CLIR
* Translation of index terms and descriptors
* CLIR involving  Asian languages  (problems and challenges)

Participation and Submission of Papers

Participation is limited to 30 persons. Participants will be selected by the
organizing committee, based on submitted papers.  Participants will be
expected to contribute to the workshop by either presenting a talk or
taking part in the discussions.

Researchers interested in participating in the workshop are invited to
submit long abstracts (up to three pages) on the listed research topics.
 Submissions may be sent by e-mail  (PostScript files) or as hardcopies
 (in triplicate) to the workshop organiser.  In the case where you use
non-Roman fonts, hardcopies are preferred.

The submissions will be reviewed and the accepted papers will be published
in the workshop proceedings. Participants selected for giving a talk,  will
have
 to submit a full paper (up to 8 pages) for the workshop proceedings.
For more information about the workshop, please contact the Workshop
Organiser.

Important Dates

Abstracts due by:  May 31, 1999.
Notification of acceptance:  June 30, 1999.
 Camera-ready version of Final Paper due: August  2, 1999.
Main MT Summit: September 13-17, 1999.
Date of the Workshop: September 17,1999

Organising Committee
* Sophia Ananiadou, European Media Lab, Germany
* Christian Jacquemin, LIMSI, France
* Yoshihiko Hayashi, NTT Cyberspace Labs, Japan
* Mun Kew Leong, Kent Ridge Digital  Labs,  Singapore
* Sung Hyon Myaeng, Chungnam National University, Korea
* Hsin-Hsi Chen, National Taiwan University, Taiwan

Workshop Organiser
Please send abstracts / papers to:
Sophia Ananiadou
European Media Lab (EML)
Villa Bosch, Schloss-Wolfsbrunnenweg 33
D-69118  Heidelberg
Germany
Fax: +49-6221-533-298
Email: Sophia.Ananiadou at eml.villa-bosch.org