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, lecturer
- Miles Osborne, reader
- Barry Haddow, postdoctoral researcher
- Adam Lopez, postdoctoral researcher
- Abhishek Arun, graduate student
- Michael Auli, graduate student
- Alexandra Birch, graduate student
- Loïc Dugast, graduate student
- Hieu Hoang, graduate student
- Abby Levenberg, graduate student
- Philip Williams, graduate student
Alumni
Visitors
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.
Activities
Related Organizations