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 persuits 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, lecturer
- Trevor Cohn, postdoctoral researcher
- Phil Blunsom, postdoctoral researcher
- Adam Lopez, postdoctoral researcher
- Barry Haddow, postdoctoral researcher
- Abhishek Arun, graduate student
- Alexandra Birch Mayne, graduate student
- Loic Dugast, graduate student
- Hieu Hoang, graduate student
- David Talbot, graduate student
- Josh Schroeder, research fellow
Alumni
Projects
- AGILE/GALE: DARPA challenge to translate Arabic-English, Chinese-English. Text to text translation, speech to text translation, distillation. (press)
- EuroMatrix: 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 will create 380 MT systems, which is all pairs of the 20 official EU languages (demo)
- Demeter: EPSRC project looking at large-scale discriminative training.
Activities
Related Organizations
