Machine Translation @ the NCLT & the CNGL

Dublin City University, Ireland

Home People Projects Publications Events Announcements Links
-- current projects --
  Confident MT

-- completed projects --
  Sign language

  DVD subtitling
  EBMT & Marker

  Hybrid EBMT-SMT
Title:Prospect: Probabilistic Solutions to the Problems of Computerised Translation
Duration:September 1st 2005 -- August 31st 2009
Funded by:Science Foundation Ireland's Investigator Programme
People:Hany Hassan, Yanjun Ma, Mary Hearne, Nicolas Stroppa, Andy Way
Collaboration:Khalil Sima'an, University of Amsterdam
Description:Today, data-driven Natural Language Processing (NLP) is by far the predominant research paradigm in the field of NLP, and Machine Translation (MT) is no exception in this respect. The MT team at NCLT is a leading and recognized team in the field of data-driven MT, especially in Data-Oriented Translation (DOT) and Example-Based Machine Translation (EBMT). These approaches have been successfully applied to several European Languages (mainly English, French, and German).
 This project aims at (i) continuing this line of research from both a theoretical and practical point-of-view, (ii) adapting these approaches to Arabic<->English and Chinese<->English Machine Translation, for which we have seen a huge growth in demand for automation of the translation process.
Support:ICHEC: Irish Centre for High-End Computing
Last update: June 16 2007
Related Sites: NCLT | School of Computing | School of Applied Languages and Intercultural Studies | Dublin City University