[MT-List] Controlled Language Translation

[Andy.Way]

                         Preliminary Call For Papers

  Joint Conference combining the 7th International Workshop of the European
     Association for Machine Translation and the 4th Controlled Language
                           Applications Workshop

           Main Conference theme: Controlled Language Translation

                  Location: Dublin City University, Ireland

                         Dates: 15th-17th May, 2003

=09=09Conference URL: http://www.eamt.org/eamt-claw03/

This document constitutes the preliminary call for papers for the 2003 join=
t
conference of the European Association for Machine Translation (EAMT) and
the Controlled Language Applications Workshop (CLAW). The main theme of the
conference is controlled translation. It is envisaged that papers addressin=
g
this theme will be featured on the middle day of the conference, with the
first day given over to more general papers on machine translation (MT), an=
d
the final day dedicated to other papers focussing more on controlled
language issues.

Over the years, there have been many conferences on MT, involving rule-base=
d
approaches, statistical and example-based approaches, hybrid and
multi-engine approaches as well as those limited to particular sublanguage
domains. In addition, there has been an increased level of interest in
controlled languages, culminating in the series of Workshops on controlled
language applications. These have given impetus to both monolingual and
multilingual guidelines and applications using controlled language, for man=
y
different languages.

Controlled languages are subsets of natural languages whose grammars and
dictionaries have been restricted in order to reduce or eliminate both
ambiguity and complexity. Traditionally, controlled languages fall into two
major categories: those that improve readability for human readers,
particularly non-native speakers, and those that improve computational
processing of the text. It is often claimed that machine-oriented controlle=
d
language should be of particular benefit when it comes to the use of
translation tools (including machine translation, translation memory,
multilingual terminology tools etc.).

Experience has shown that high quality MT systems can be designed for
specialized domains (e.g. METEO). However, the area of controlled
translation has remained relatively unaddressed. This is rather strange
given its undoubted importance. Such examples that exist use rule-based MT
(RBMT) systems to translate controlled language documentation, e.g.
Caterpillar's CTE and CMU's KANT system, and General Motors CASL and
LantMark, etc. However, fine-tuning general systems designed for use with
unrestricted texts to derive specific, restricted applications is complex
and expensive.

There are several examples of using Translation Memory (TM) tools in a
controlled language workflow, yet these have been primarily for combining T=
M
and MT tools. Very few attempts have been made where Example-based MT (EBMT=
)
systems have been designed specifically for controlled language application=
s
and use. This is even harder to fathom: using traditional RBMT systems lead=
s
to the well-known `knowledge acquisition bottleneck', which can be overcome
by using corpus-based MT technology. Furthermore, the quality of EBMT (and
Translation Memory) systems depends on the quality of the reference
translations in the system database; the more these are controlled, the
better the expected quality of translation output by the system.

The primary aim of this unique conference, therefore, is to elicit papers o=
n
controlled translation, and provide a forum in which the problems may be
outlined, possible solutions proposed, and in general to bring together
developers, implementors, researchers and end-users from the publications,
authoring, translation and localization fields to discuss how ideas from
both the authoring and translation camps might be integrated in this common
area. Some specific topics which might be addressed include:

   * What is controlled translation?
   * RBMT and controlled translation.
   * TM/EBMT and controlled translation.
   * Influence and interplay of controlled language upon both
     source-language parsing and target-language generation in an MT system=
.
   * Role of the lexicon in controlled translation.
   * Can we expect better controlled translations from a hybrid approach? O=
r
     from a multi-engine approach?
   * Towards a Roadmap for controlled translation - the way ahead?

In addition, we welcome contributions on MT as well as on controlled
language which do not address the main theme per se. Suitable example topic=
s
include, but are not restricted to, the following:

Machine Translation

   * MT for the Web;
   * Practical MT systems;
   * Methodologies for MT;
   * Speech and dialogue translation;
   * Text and speech corpora for MT and knowledge extraction from corpora;
   * MT evaluation techniques and evaluation results;
   * MT postediting.

Controlled Language

   * Examples of controlled languages: their definition, by whom, and
     intended usage;
   * Consequences for technical authors and implications for Natural
     Language Processing;
   * Practical experiences of teaching and using controlled languages;
   * Application of controlled languages in speech systems.

Finally, intentions to present system demonstrations are particularly
welcomed. Abstracts for demos must not exceed 400 words. Developers should
outline the design of their system and provide sufficient details to allow
the evaluation of its validity, quality, and relevance to controlled
language. Pointers to web sites running the demo preview and/or screen
camcorder video clips will also be helpful.

Programme

It is anticipated that papers which address the central theme of the joint
conference, controlled translation, will be featured on the middle day of
the three. The first day will be given over to papers focussing primarily o=
n
MT, and the third day will feature papers focussing more on controlled
language issues. Papers will each be allowed 30 minutes, including
questions.

Invited Speakers

We are pleased to announce that invited speakers for the conference will
include Steven Krauwer, University of Utrecht and Coordinator of ELSNET, an=
d
Lou Cremers, Oc=E9 Technologies. We anticipate that the speakers will provi=
de
a sharp and stimulating focus on the theme of the conference.

Attendance Fees and Registration

Details of registration procedures, including registration fees, will be
announced as soon as they become available. It is anticipated that
participants will be able to register for the MT part, the joint session,
and the CLAW day separately, or in various combinations. But we expect by
far the best value option to be a package deal which allows attendance at
all three days. In addition, there will be a discount for early
registration, the deadline for which will be 31st March, 2003.

Important Dates

              Draft papers due             29th November, 2002
                Reviews due                 31st January, 2003
         Notification of acceptance        14th February, 2003
 Camera-ready papers & pre-registration due  31st March, 2003

Submission Details

Papers accepted for the conference will be published in a proceedings volum=
e
available to all attendees. Papers should describe unique work not publishe=
d
before. Papers that are being submitted to other conferences should include
this information on the first page. Paper submissions should follow these
conventions:

   * Maximum length is 4000 words
   * 8.5" x 11" page size
   * Single-column, single-spaced, 1" margins
   * 12 point font
   * Include title, authors, and contact info centered at the top of the
     first page
   * Include an abstract of about 100 words

Electronic submission is strongly encouraged. We prefer PDF files, sent as
EMail attachments. Electronic submissions should be sent to Eric Nyberg
(ehn@cs.cmu.edu), with `Submission for EAMT-CLAW 2003' in the Subject line =
of=20
the email.

Papers for each of the three sessions will be reviewed separately. Please
indicate which session your paper is to be reviewed under.

Please note that papers will not be accepted (at the camera-ready copy
stage) unless at least one of the authors has pre-registered for the
conference.

Organizing Committee

The Organizing Committee consists of:

   * John Hutchins (WJHutchins@compuserve.com), on behalf of the EAMT,
   * Arendse Bernth (arendse@us.ibm.com), on behalf of CLAW,

together with three local Organizers:

   * Dorothy Kenny (Dorothy.Kenny@dcu.ie)
   * Sharon O'Brien (Sharon.OBrien@dcu.ie)
   * Andy Way (away@computing.dcu.ie)

Contact any of the above for more details.

Programme Committee

The programme committee will include, among others:

Jeff Allen (Mycom France and MIT2, France), Arendse Bernth (IBM Watson
Research, USA), Kurt Godden (Lockheed Martin, USA), John Hutchins (EAMT
President, University of East Anglia, UK), Dorothy Kenny (Dublin City
University, Ireland), Jaro Lajovic (Dept. of Intelligent Systems Institute,
Ljubljana, Slovenia), Bente Maegaard (Center for Language Technology,
Copenhagen, Denmark), Teruko Mitamura (Carnegie Mellon University, USA),
Eric Nyberg (Carnegie Mellon University, USA), Sharon O'Brien (Dublin City
University, Ireland), Ursula Reuther (IAI, University of Saarbr=FCcken,
Germany), Joerg Sch=FCtz (IAI, University of Saarbr=FCcken, Germany), Harol=
d
Somers (UMIST, UK), Andy Way (Dublin City University, Ireland), Rick Wojcik
(Boeing, USA)