Corpora: CfP: MT Special Issue on Spoken Language Translation

Steven Krauwer (Steven.Krauwer@let.ruu.nl)
Thu, 12 Mar 1998 09:43:42 +0100

CALL FOR SUBMISSIONS

MACHINE TRANSLATION

SPECIAL ISSUE ON SPOKEN LANGUAGE TRANSLATION

Guest editor: Steven Krauwer (Utrecht University)

Guest editorial board:
Doug Arnold (University of Essex)
Pascale Fung (HKUST, Hong Kong)
Walter Kasper (DFKI, Saarbrucken)
Alon Lavie (CMU, Pittsburgh)
Lori Levin (CMU, Pittsburgh)
Hermann Ney (RWTH, Aachen)
Harold Somers (UMIST, Manchester)

Some 15 years ago, when Machine Translation had become
fashionable again in Europe, few people would be prepared to
consider seriously embarking upon spoken language translation
research. After all, where both machine translation of written
text, and speech understanding and production (despite important
achievements) were still quite far from showing robustness in
domain-independent applications, it seemed clear that putting
three not even halfway understood technologies together would be
premature, and bound to fail. Since then, the world has changed.

Many researchers, both in academia and in industry, have taken up
the challenge to build systems capable of translating spoken
language. Does that mean that most of the problems involved in
speech-to-text, text-to-text translation, and text-to-speech have
been solved? The answer is no: although we have made a tremendous
progress, both from a scientific and from a technological point
of view, many of the fundamental problems in MT and in speech
understanding remain unsolved.

Yet a certain degree of optimism is justified here. First of all,
it is clear that on the whole general expectations of what MT
will do are changing. Where in the past the ultimate goal of MT
seemed to be to provide a perfect, but cheaper and faster
alternative to the human translator, there is now a clear shift
from the ideal of fully automated high quality translation of
unrestricted texts to the more practical problem of overcoming
the language barriers we encounter in various situations. This
shift of focus allows us to partition the problem we address into
a series of smaller ones, the solution to which may be within our
reach.

This applies both to spoken and written language translation. If
we look at spoken communication between human beings with
different native languages, very often the main success criterion
for this communication is not whether or not the individual
utterances produced by the participants have been expressed or
understood without errors (which will rarely be the case), but
rather whether the intended goal of the communication has been
attained (hotel room reservation, airline information, etc). This
observation is extremely important when we try to set our goals
for spoken translation systems. Once we have realized that
communication takes place in a specific context, with a specific
goal, and have accepted that sentence-by-sentence linguistically
correct translation is not a necessary condition for successful
multilingual communication, we can start exploiting the full
potential of spoken dialogues in human-human and human-machine
interaction: the basic structure of dialogues, the ways to
control dialogue flow, the possibility for repair.

A workshop dedicated to spoken language translation, organized in
conjunction with EACL/ACL 1997 in Madrid, showed that there was a
keen interest in the topic, and that many acedemic and industrial
research teams have interesting results to report.

Therefore we feel that the time has come to dedicate a special
issue of the journal Machine Translation to this topic, and we
are inviting high-quality, previously unpublished research papers
addressing problems in the whole field of spoken language
translation. (Note: authors who had papers accepted for the
Madrid workshop are especially encouraged to submit papers which
have developed out of their workshop contributions, though they
should note that we do not intend simply to reprint the workshop
papers in their original form.)

We are especially interested in papers addressing problems or
solutions that are typical for spoken language translation (as
opposed to written language translation).

FORMAT FOR SUBMISSION:

Please consult the journal's web pages:
home page:
http://kapis.www.wkap.nl/journalhome.htm/0922-6567
Instructions for Authors:
http://kapis.www.wkap.nl/kaphtml.htm/IFA0922-6567
LaTeX style files:
http://kapis.www.wkap.nl/jrnlstyle.htm/0922-6567

Articles should be submitted DIRECTLY TO THE PUBLISHERS, either
by e-mail to ELLEN.KLINK@wkap.nl, with the subject header
"Submission to COAT Speech special issue", or in hard-copy to
either of the following addresses:

Machine Translation Editorial Office, Machine Translation Editorial Office
Kluwer Academic Publishers Kluwer Academic Publishers
P.O. Box 990, P.O. Box 230
3300 AZ Dordrecht, Accord, MA 02018-023
The Netherlands U.S.A.

The journal is typeset using LaTeX, so the preferred medium for
submission of articles in electronic format is LaTeX source
(using the Kluwer style file) or gzipped postscript. If
submitting hard-copy, four copies of the paper are required. The
length of the papers should be approximately 10-20 pages if using
the Kluwer style file (around 20k words). Authors are requested
to send a copy of an Abstract of not more than 200 words to the
guest editor Steven.Krauwer@let.ruu.nl or in hard-copy to

Steven Krauwer,
Utrecht Institute of Linguistics OTS,
Trans 10,
3512 JK Utrecht,
The Netherlands

SUBMISSION DEADLINE:

Submissions should be received by July 1 1998. Papers will be
reviewed by at least three members of the editorial board. We are
aiming for publication as issue 3 or 4 of volume 13 (Autumn or
Winter, 1998).