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 Conference URL: http://www.eamt.org/eamt-claw03/ This document constitutes the preliminary call for papers for the 2003 joint 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 addressing 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), and 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-based 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 many 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 controlled 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 TM and MT tools. Very few attempts have been made where Example-based MT (EBMT) systems have been designed specifically for controlled language applications and use. This is even harder to fathom: using traditional RBMT systems leads 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 on 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? Or 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 topics 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 on 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, and Lou Cremers, Oce Technologies. We anticipate that the speakers will provide 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 volume available to all attendees. Papers should describe unique work not published 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 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, 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 Saarbruecken, Germany), Joerg Schuetz (IAI, University of Saarbruecken, Germany), Harold Somers (UMIST, UK), Andy Way (Dublin City University, Ireland), Rick Wojcik (Boeing, USA)