- Statistical Machine Translation
Philipp Koehn, a professor in the Department of Computer Science, is recognized worldwide for his leading research in and applications for developing and understanding data-driven methods to solve long-standing, real-world challenges of machine translation and machine learning.
Today’s deluge of digital information is both a product of and engine for nearly every function of modern society. Koehn’s area of renowned expertise—statistical machine translation or translating text from one human language to another by a computer—is vital to addressing the ever-expanding need for natural language processing and machine learning.
Koehn leads a team of 20 Johns Hopkins researchers to develop the first-ever information retrieval and translation system for languages that are not widely used around the world. Funded by a $10.7 million grant from the Office of the Director of National Intelligence, the project aims to drastically reduce the time and the amount of information needed for intelligence agents to translate languages, such as such as Kurdish, Serbo-Croatian, Khmer, Hmong, and Somali, which are spoken by millions of people but not prevalent in written material.
He is affiliated with the Whiting School’s Center for Language and the University of Edinburgh, U.K., where he has held the position of professor and chair of machine translation, School of Informatics, since August 2012. The author of the field’s seminal textbook on the subject, “Statistical Machine Translation”, (Cambridge University Press, 2009), Koehn also is the founder and webmaster of the field’s website, Statistical Machine Translation. In 2016, he co-authored “Syntax-based Statistical Machine Translation, Synthesis Lectures on Human Language Technologies” (Morgan and Claypool Publishers) and holds or co-holds five patents for statistical models for machine translation.
The 2015 winner of the Award of Honor, International Association for Machine Translation, Koehn was one of three finalists for the 2013 European Inventor Award. At the 2011 META NET, the conference for the Multilingual Europe Technology Alliance, Koehn won the META First Prize for Moses, his open source toolkit for statistical machine translation. His additional contributions to the field through refereed journals, panels, presentations, and web tutorials are extensive. Koehn, who has appeared on CNN and other media outlets, has given numerous invited talks, most recently by Amazon (2018) and Google (2017) on the challenges for neural machine translation.
Koehn serves on the editorial boards for multiple journals, among them: Transaction of the Association of Computational Linguistics; Machine Translation Journal; Artificial Intelligence Review; Computation, Corpora, Cognition, and ACM Transactions on Asian and Low-Resource Language Information Processing. Koehn is a noted leader within the Association for Computational Linguistics (ACL). He is president of the ACL Special Interest Group on Machine Translation (since 2009) and former president of the ACL Special Interest Group on Linguistic Data and Corpus-Based Approaches to natural language processing. His ACL leadership includes co-chairing the series of ACL workshops and conferences on Machine Translation since 2005 and chairing several ACL workshops on Statistical Machine Translation. In addition, Koehn has chaired the Machine Translation Marathon and co-chaired Machine Translation Marathon in the Americas.
He received a MS in Computer Science (1996) from the University of Tennessee, a Diplom, Computer Science from the Universität Erlangen-Nürnberg, and PhD in Computer Science from the University of Southern California.