Statistical Machine Translation at the University of Edinburgh

The dream of automatically translating documents from foreign languages into English (or between any two languages) is one of the oldest pursuits of artificial intelligence research. Now, armed with vast amounts of example translations and powerful computers, we can witness significant progress toward achieving that dream. Statistical analysis of bilingual parallel corpora allow for the automatic construction of machine translation systems. Already, for language pairs such as Chinese-English or Arabic-English, statistical systems are the best machine translation systems currently available.



  • Abhishek Arun (PhD student), now research scientist at Bing
  • Michael Auli, (PhD student), now at Microsoft Research
  • Amittai Axelrod (MSc student), now PhD student at University of Washington
  • Phil Blunsom (postdoctoral researcher), now lecturer at Oxford University
  • Chris Callison-Burch (PhD student), now assistant professor at University of Pennsylvania
  • Trevor Cohn (postdoctoral researcher), now lecturer at University of Sheffield
  • Loďc Dugast (PhD student), now at Systran
  • Yang Gao (MSc student), now PhD student at ISI
  • Kenneth Heafield, (research associate), now postdoctoral researcher at Stanford
  • Abby Levenberg (PhD student), now postdoctoral researcher at Oxford University
  • Adam Lopez (postdoctoral researcher), now assistant research professor at Johns Hopkins University
  • Josh Schroeder (MSc student), now software engineer at Google
  • David Talbot (PhD student), now research scientist at Google
  • Oliver Wilson, now in industry in Australia


  • Marcin Junczys-Dowmunt (lecturer, Adam Mickiewicz University, Poland) March-May 2014
  • Rico Sennrich (researcher, U. Zurich), Nov 2013-Apr 2015
  • Chara Tsoukala (PhD student, U Groningen), Feb-Aug 2013
  • Youzheng Wu (NICT), Mar-Jun 2013
  • Jesús González Rubio (researcher, Universidad Politécnica de Valencia), Jun-Aug 2010
  • Anoop Sarkar (associate professor, Simon Fraser U.), Sep 2009-Apr 2010
  • Andreas Zollmann (PhD student, CMU), Jul-Aug 2009
  • Juri Ganitkevitch (Phd student, Johns Hopkins), Jul-Aug 2009
  • Chris Dyer (Phd student, U. Maryland), Feb-Mar 2009


  • CASMACAT, 2011-2014: Cognitive analysis and statistical methods for advanced computer aided translation
  • MateCat, 2011-2014: Machine translation enhanced computer assisted translation
  • EU BRIDGE, 2012-2015: Speech translation
  • ACCEPT, 2012-2015: Automated community content editing portal
  • MosesCore, 2012-2015: Support action for open source machine translation development, evaluation, and dissemination
  • Thunderbolt/BOLT, 2011-2013: DARPA challenge to translate Chinese and Arabic dialects
  • EuroMatrixPlus, 2009-2012: Bringing machine translation for all European Language Pairs to the User
  • LetsMT, 2010-2013: Platform for online sharing of training data and building user tailored MT
  • AGILE/GALE, 2005-2011: DARPA challenge to translate Arabic-English, Chinese-English. Text to text translation, speech to text translation, distillation. (press)
  • EuroMatrix, 2006-2009: Text to text translation between EU languages with focus on problems associated with translating into languages other than English. As part of the project we created 462 MT systems, which is all pairs of 22 official EU languages (demo)
  • Demeter, 2006-2009: EPSRC project looking at large-scale discriminative training.



Related Organizations

Page last modified on June 16, 2014, at 08:06 PM