[Apologies for multiple postings] Call for participation
3rd Workshop on Example-Based Machine Translation "Going open-source to revive EBMT" Business School, Room QG21 Dublin City University, Dublin 9, Ireland November 1213, 2009 See workshop website: http://www.computing.dcu.ie/~mforcada/ebmt3/ for details and updates. *** Workshop rationale *** Following two successful EBMT workshops in 2001 at the MT Summit VIII in Santiago de Compostela, Spain, and in 2005 at the MT Summit X in Phuket, Thailand, this is the third workshop of its kind. Many things have happened since 2005. The last few years have witnessed a decline in example-based machine translation (EBMT) research and statistical machine translation (SMT) has almost completely taken over the corpus-based machine translation arena, with many EBMT practitioners moving into hybrid approaches integrating EBMT with other approaches, mostly (but not only) SMT. Not having a clear definition of what EBMT is has also contributed to this lack of visibility. In fact, research that would have been considered EBMT has been published without the EBMT label. Is the success of SMT due to the fact that it is the best way to do corpus-based machine translation or is it because many SMT software packages are readily available to researchers under free/open-source licences that allow use as well as collaborative improvement? Shouldn't EBMT practitioners start to think about putting together their tools, their engines and their data and releasing them under open licenses to extend their use both in academia and in industry? The pressure on machine translation researchers to prove their results through detailed empirical evaluation is growing. But the validity of empirical results hinges on reproducibility. Turning our experimental research into packages and tools that other researchers can use and improve is a challenge but it is not infeasible as SMT practitioners have shown. *** Preliminary programme *** THURSDAY NOVEMBER 13 08.30 Registration 09.15 Opening address 09.30 Invited talk: Sadao Kurohashi, "Fully Syntactic Example-based Machine Translation" 10.30 COFFEE BREAK Session 1: Hybrid Approaches to EBMT 11.00 Stephen Clark and James Smith. EBMT for SMT: A New EBMT-SMT Hybrid 11.30 Felipe Sánchez-Martínez, Mikel L. Forcada and Andy Way. Hybrid Rule-Based -- Example-Based MT: Feeding Apertium with Sub-sentential Translation Units 12.00 Declan Groves, Sergio Penkale, Ankit Srivastava and John Tinsley. Evaluating Syntax-Driven Approaches to Phrase Extraction for MT (Regular paper) 12.30 LUNCH BREAK Session 2: Open-Source EBMT packages and tools 14.00 Aaron Phillips and Ralf Brown. Cunei Machine Translation Platform: System Description 14.30 David Farwell and Lluís Padró. FreeLing: From a multilingual open-source analyzer suite to an EBMT platform 15.00 Adrien Lardilleux, Jonathan Chevelu, Yves Lepage, Ghislain Putois and Julien Gosme. Lexicons or phrase tables? An investigation in sampling-based multilingual alignment 15.30 COFFEE BREAK Roundtable discussion: "Going open-source to revive EBMT? 16.00 Seeding talks: * Andy Way: "Open research questions for EBMT" * Mikel L. Forcada: "Why free/open source EBMT?" 16.20 Panel: Ralf Brown, Yves LePage, Sadao Kurohashi 16.40 Open discussion 17.40 END OF THURSDAY PROGRAM 19.30 CONFERENCE DINNER (venue to be announced) FRIDAY NOVEMBER 13 Session 3: "Pure" EBMT 09.30 Harold Somers, Sandipan Dandapat and Sudip Naskar. A review of EBMT using proportional analogies 10.00 Maarten van Gompel, Antal van den Bosch and Peter Berck. Extending Memory-Based Machine Translation to Phrases 10.30 Vincent Vandeghinste and Scott Martens. Top-down Transfer in Example-based MT 11.00 COFFEE BREAK Session 4: Applications 11.30 Julien Gosme, Yves Lepage and Adrien Lardilleux. Translation of sublanguage by subgrammars 12.00 Marian Flanagan. Using Example-Based Machine Translation to translate DVD Subtitles 12.30 Closing address 13.00 Workshop close *** Registration *** Registration will soon be available through the workshop webpage, http://www.computing.dcu.ie/~mforcada/ebmt3/, as well as on-site at the conference venue. Registration fees * Regular: 120.00 * Student: 100.00 Registration fees include a printed and electronic version of workshop proceedings, all three coffee breaks, lunch on Thursday, and conference dinner on Thursday. *** Accomodation *** We are arranging for a special rate at a major hotel within walking distance to the venue. Details will be posted at the website as soon as they are available. *** Travel advisory *** If you plan to stay in Dublin for the weekend, be advised that on Saturday 14 there is a Ireland-France FIBA World Cup match that may be attended by visitors from Continental Europe. Book your flights early. Programme co-chairs: * Mikel L. Forcada (DLSI, Universitat d'Alacant and CNGL, Dublin City University) * Andy Way (CNGL, Dublin City University) Programme committee: * Sivaji Bandyopadhyay, Jadavpur University, Kolkata, India * Ralf Brown, Carnegie Mellon University, Pittsburgh, USA. * Michael Carl, Copenhagen Business School, Denmark * David Farwell, ICREA-UPC, Barcelona, Spain * Mikel Forcada, Universitat d'Alacant, Spain and Dublin City University, Ireland * Declan Groves, Traslán, Ireland * John Hutchins, Norwich, U.K. * Sadao Kurohashi, Kyoto University, Japan. * Yves Lepage, Université de Caen, France. * Harold Somers, Dublin City University, Dublin, Ireland * Eiichiro Sumita, ATR, Kyoto, Japan. * Andy Way, Dublin City University, Ireland Local organising committee: * Sudip Naskar * Sandipan Dandapat * Ankit Srivastava * Cara Greene * Eithne McCann Sponsored by: * The Centre for Next Generation Localisation * The European Association for Machine Translation * Science Foundation Ireland * Dublin City University Mikel L. Forcada <[email protected]> Dept. Llenguatges i Sistemes Informàtics Universitat d\\\'Alacant, E-03071 Alacant (Spain) Tel.: +34 96 590 9776 Fax: +34 96 590 9326 _______________________________________________ Mt-list mailing list
