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.

People

• Philipp Koehn, reader
• Miles Osborne, reader
• Barry Haddow, postdoctoral researcher
• Michael Auli, graduate student
• Christian Buck, graduate student
• Loïc Dugast, graduate student
• Liane Guillou, graduate student
• Eva Hasler, graduate student
• David Matthews, graduate student
• Philip Williams, graduate student
• Oliver Wilson, research associate
• Herve Saint-Amand, research associate

Alumni

• Abhishek Arun (PhD student), now research scientist at Bing
• Amittai Axelrod (MSc student), now PhD student at University of Washington
• Alexandra Birch (PhD student), now postdoc at the University of Edinburgh (with Mark Steedman)
• Phil Blunsom (postdoctoral researcher), now lecturer at Oxford University
• Chris Callison-Burch (PhD student), now associate research professor at Johns Hopkins University
• Trevor Cohn (postdoctoral researcher), now lecturer at University of Sheffield
• Hieu Hoang (PhD student), now at Asia Online
• Yang Gao (MSc student), now PhD student at ISI
• Abby Levenberg (PhD student), now postdoc at Oxford University
• Adam Lopez (postdoctoral researcher), now a research scientist at Johns Hopkins University
• Josh Schroeder (MSc student), now software engineer at Google
• David Talbot (PhD student), now research scientist at Google

Visitors

• Kenneth Heafield (PhD student, CMU), Jul-Dec 2011
• 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

Projects

• 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.

Publications

Activities

• Weekly Meeting Group
• Moses MT System
• Computer Aided Translation
• JHU Summer Workshop 2010: Models of Synchronous Grammar Induction for SMT
• JHU Summer Workshop 2006: Open Source Toolkit for Statistical Machine Translation
• Sixth workshop on Machine Translation 2011
• Fifth workshop on Machine Translation 2010
• Fourth workshop on Machine Translation 2009
• Third workshop on Machine Translation 2008
• Second workshop on Machine Translation 2007
• Workshop on Machine Translation 2006
• Workshop on Parallel Text 2005

Related Organizations

• University of Edinburgh
• School of Informatics
• Institute for Communicating and Collaborative Systems (ICCS)
• Human Communication Research Centre (HCRC)
• ACL Special Interest Group on Machine Translation