Research Interests

Natural Language Processing, Machine Translation, Machine Learning

My research focuses on developing and understanding data-driven methods to solve long-standing real-world problem such as machine translation.

Education

Doctor of Philosophy, Computer Science

Department of Computer Science, University of Southern California
Thesis title: Noun Phrase Translation
Thesis advisor: Prof. Kevin Knight
December 2003

Diplom, Computer Science

Department of Computer Science, Universität Erlangen-Nürnberg
Thesis title: Statistical and Model-Based Learning Methods for Extending Unification Grammars
Thesis advisors: Prof. Günther Görz
October 1996

Master of Science, Computer Science

Department of Computer Science, University of Tennessee, Knoxville
Thesis title: Combining Genetic Algorithms and Neural Networks
Thesis advisor: Prof. Bruce MacLennan
(on Fulbright Grant)
December 1994

Professional Experience

Postdoctorial Associate

Massachusetts Institute of Technology, Cambridge, MA
since February 2004

Research Assistant

USC Information Sciences Institute, Los Angeles, CA
August 1997 - December 2003

Summer Research Intern

Whizbang! Labs, Provo, UT
Under guidance of Dallan Quass
May-August 2000

Summer Manager

AT&T Research - Labs, Florham Park, NJ
Under guidance of Steve Abney, Michael Collins and Julia Hirschberg
May-August 1999

Internet Consultant

Netzmarkt, Erlangen, Germany
May 1996 - June 1997 (full time)
July 1997 - December 2000 (part time)

Teaching Assistant

Computer Science Department
University of Tennessee, Knoxville, TN
Fall 1994

Teaching Assistant

Mathematics Department
Universität Erlangen-Nürnberg, Germany
Winter 1992-1993 and Summer 1993

Conference Papers

Philipp Koehn: "Statistical Significance Tests for Machine Translation Evaluation", Conference on Empirical Methods in Natural Language Processing (EMNLP), 2004

Philipp Koehn: "Pharaoh: a Beam Search Decoder for Phrase-Based Statistical Machine Translation Models" Meeting of the American Association for Machine Translation (AMTA), 2004

Philipp Koehn and Kevin Knight: "Feature-Rich Statistical Translation of Noun Phrases", 41st Annual Meeting of the Association for Computational Linguistics (ACL), 2003

Philipp Koehn, Franz Josef Och, and Daniel Marcu: "Statistical Phrase-Based Translation" Human Language Technology Conference and Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), 2003

Philipp Koehn and Kevin Knight: "Empirical Methods for Compound Splitting" 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2003

Douglas W. Oard, David Doermann, Bonnie Dorr, Daqing He, Philip Resnik, Amy Weinberg, William Byrne, Sanjeev Khudanpur, David Yarowsky, Anton Leuski, Philipp Koehn, and Kevin Knight: "Desparately Seeking Cebuano" Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), 2003

Philipp Koehn: "Combining Multiclass Maximum Entropy Text Classifiers with Neural Network Voting" Portugal for Natural Language Processing, Third International Conference (PorTAL), 2002

Philipp Koehn and Kevin Knight: "Knowledge Sources for Word-Level Translation Models" Conference on Empirical Methods in Natural Language Processing (EMNLP), 2001

Philipp Koehn and Kevin Knight: "Estimating Word Translation Probabilities from Unrelated Monolingual Corpora Using the EM Algorithm" Seventeenth National Conference on Artificial Intelligence (AAAI), 2000

Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, and Kenji Yamada: "Translating with Scarce Resources" Seventeenth National Conference on Artificial Intelligence (AAAI), 2000

Philipp Koehn, Steven Abney, Julia Hirschberg, and Michael Collins: "Improving Intonational Phrasing with Syntactic Information" International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2000

Philipp Koehn: "Genetic Encoding Strategies for Neural Networks" Sixth International Conference on Information Processing and Management of Uncertainty (IPMU), 1996

Journal Article

Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, and Kenji Yamada: "Translation with Scarce Bilingual Resources" Machine Translation 17: 1-17, 2002

Refereed Workshop Paper

Philipp Koehn and Kevin Knight: "Learning a Translation Lexicon from Monolingual Corpora" 40th Annual Meeting of the Association for Computational Linguistics (ACL), Workshop on Unsupervised Lexical Acquisition, 2002

Tutorials

Kevin Knight and Philipp Koehn: "What's New in Statistical Machine Translation?" Human Language Technology Conference and Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), 2003

Kevin Knight and Philipp Koehn: "Introduction to Statistical Machine Translation" Machine Translation Summit IX, 2003; Human Language Technology Conference and Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), 2004; Meeting of the American Association for Machine Translation (AMTA), 2004