Philipp Koehn is a Professor at the School of Informatics where he holds the Personal Chair of Machine Translation. He received his PhD from the University of Southern California where he was a research assistant at the Information Sciences Institute (ISI) from 1997 to 2003. Koehn was a postdoctoral research associate at the Massachusetts Institute of Technology (MIT) in 2004 and joined the University of Edinburgh in 2005.
His research centres on statistical machine translation but he has also worked on speech in 1999 at AT&T Research Labs and text classification in 2000 at Whizbang Labs. Besides his research, his major contribution to the machine translation community is the preparation and release of the Europarl corpora, as well as the Pharaoh and Moses decoders --- all of which are widely used. The statistical machine translation system developed under his leadership over the last years is a top performer in recent WMT, DARPA, and IWSLT competitions. He has been organising the workshop on statistical machine translation at ACL including a shared task for translation between European languages since 2005. He authored the textbook on statistical machine translation which is widely adopted and was translated into Chinese. Koehn was the scientific coordinator of the EuroMatrix and EuroMatrixPlus projects and is currently the overall coordinator of the CASMACAT and MosesCore projects.
Machine Translation Thursday 21 March 2013, 5.15pm Informatics Forum, G.07/G.07A, 10 Crichton Street, Edinburgh EH8 9AB
Statistical Machine Translation has made great progress over the last years. I will survey the field and some of my recent work on modelling, parameter training and efficient handling of large models, with a focus on the current open problems and promising directions to address them.