Philipp Koehn

philipp koehn

Professor at the University of Edinburgh
Chair of Machine Translation
School of Informatics
10 Crichton Street, room 4.19
Edinburgh, EH8 9AB, United Kingdom
Fax: +44 131 650-6626
Fon: +44 131 650-8287
pkoehn@inf.ed.ac.uk
Resume
Wikipedia

My work is currently focused on statistical machine translation (video), but more broadly defined, my interest is to make use of the vast amount of information that is available in digital form.
My book on statistical machine translation is now available from amazon.uk and amazon.com.
More on the Statistical Machine Translation Group here. Come and join our weekly meeting!
software and resources

Statistical Machine Translation Website
Text book, 2010
Moses, an open source statistical machine translation system
Online Translation, based on Moses
SMT Research Survey Wiki, a Wiki covering all research publications in statistical machine translation
Online Evaluation Matrix, EuroMatrix project
Computer Aided Translation Tool Caitra, EuroMatrixPlus project
Pharaoh, 2003, 2004, a beam search decoder for phrase-based statistical machine translation models (replaced by Moses)
Parallel Corpus European Parliament Proceedings, 2001, 2003, 2007.
German-English Parallel Corpus "de-news", Daily News 1996-2000, 2000.

teaching

Machine Translation, Spring 2009-2011.
Advanced Natural Language Processing,
Fall 2008-2012.
Empirical Methods in Natural Language
Processing, Spring 2007, 2008.
Data Intensive Linguistics, Spring 2006.
Computer Programming, Fall 2005-2007.

advising

Maria Nadejde, PhD student, 2012-
Liane Guillou, PhD student, 2012-
Christian Buck, PhD student, 2011-
Eva Hasler, PhD student, 2010-
Philip Williams, PhD student, 2009-
Michael Auli, PhD student, 2008-2012
Loïc Dugast, PhD student, 2006-2012
Hieu Hoang, PhD student, 2005-2011
Abhishek Arun, PhD student, 2005-2010
Information about applying to study
for a PhD or MSc in Informatics at Edinburgh. projects

CASMACAT, EC FP7 STREP, 2011-2014
MateCat, EC FP7 STREP, 2011-2014
ACCEPT, EC FP7 STREP, 2012-2015
MosesCore, EC FP7 CSA, 2012-2015
EU BRIDGE, EC FP7 IP, 2012-2015
BOLT, DARPA subcontract, 2011-
Let's MT, EC ICT-PSP, 2010-2012
EuroMatrixPlus, EC FP7 STREP, 2009-2012
EuroMatrix, EC FP6 STREP, 2006-2009
AGILE, DARPA subcontract, 2005-2011
JHU Summer Workshop, 2006
video

CNN, 2013
Research in a Nutshell
Inaugural lecture
European Inventor Award, 2013 finalist
French TV, 2010

publications

2012

Interpolated Backoff for Factored Translation Models, Philipp Koehn and Barry Haddow, Meeting of the Association for Machine Translation of the Americas (AMTA), 2012, pdf.
Language Model Rest Costs and Space-Efficient Storage, Kenneth Heafield, Philipp Koehn and Alon Lavie, Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2012, pdf.
Simulating Human Judgment in Machine Translation Evaluation Campaigns, Philipp Koehn, International Workshop on Spoken Language Translation (IWSLT), 2012, pdf.
Sparse Lexicalised Features and Topic Adaptation for SMT, Eva Hasler, Barry Haddow and Philipp Koehn, International Workshop on Spoken Language Translation (IWSLT), 2012, pdf.
The UEDIN Systems for the IWSLT 2012 Evaluation, Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals and Pawel Swietojanski, International Workshop on Spoken Language Translation (IWSLT), 2012, .
Findings of the 2012 Workshop on Statistical Machine Translation, Chris Callison-Burch, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut and Lucia Specia, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 2012, pdf, bib.
Towards Effective Use of Training Data in Statistical Machine Translation, Philipp Koehn and Barry Haddow, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 2012, pdf, bib.
GHKM Rule Extraction and Scope-3 Parsing in Moses, Philip Williams and Philipp Koehn, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 2012, pdf, bib.
Analysing the Effect of Out-of-Domain Data on SMT Systems, Barry Haddow and Philipp Koehn, Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), 2012, pdf, bib.
Extending Hiero Decoding in Moses with Cube Growing, Wenduan Xu and Philipp Koehn, The Prague Bulletin of Mathematical Linguistics, Volume 98, pages 133-142, October 2012, pdf.
Hallucinated N-Best Lists for Discriminative Language Modeling, Kenji Sagae, Maider Lehr, Emily Prud'hommeaux, Puyang Xu, Nathan Glenn, Damianos Karakos, Sanjeev Khudanpur, Brian Roark, Murat Saraçlar, Izhak Shafran, Daniel Bikel, Chris Callison-Burch, Yuan Cao, Keith Hall, Eva Hasler, Philipp Koehn, Adam Lopez, Matt Post, Darcey Riley, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012, pdf.
Continuous Space Discriminative Language Modeling, Puyang Xu, Sanjeev Khudanpur, Maider Lehr, Emily Prud'hommeaux, Nathan Glenn, Damianos Karakos, Brian Roark, Kenji Sagae, Murat Saraçlar, Izhak Shafran, Dan Bikel, Chris Callison-Burch, Yuan Cao, Keith Hall, Eva Hasler, Philipp Koehn, Adam Lopez, Matt Post, Darcey Riley, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012, pdf.
Semi-Supervised Discriminative Language Modeling for Turkish ASR, Arda Çelebi, Haçim Sak, Erinç Dikici, Murat Saraçlar, Maider Lehr, Emily Tucker Prud'hommeaux, Puyang Xu, Nathan Glenn, Damianos Karakos, Sanjeev Khudanpur, Brian Roark, Kenji Sagae, Izhak Shafran, Dan Bikel, Chris Callison-Burch, Yuan Cao, Keith Hall, Eva Hasler, Philipp Koehn, Adam Lopez, Matt Post, Darcey Riley, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012, pdf.
Deriving conversation-based features from unlabeled speech for discriminative language modeling, Damianos Karakos, Brian Roark, Izhak Shafran, Kenji Sagae, Maider Lehr, Emily Prud'hommeaux, Puyang Xu, Nathan Glenn, Sanjeev Khudanpur, Murat Saraclar, Dan Bikel, Mark Dredze, Chris Callison-Burch, Yuan Cao, Keith Hall, Eva Hasler, Philip Koehn, Adam Lopez, Matt Post and Darcey Riley, InterSpeech, 2012, pdf.

2011

Soft Dependency Constraints for Reordering in Hierarchical Phrase-Based Translation, Yang Gao, Philipp Koehn and Alexandra Birch, Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP), pdf, bib.
Left Language Model State for Syntactic Machine Translation, Kenneth Heafield, Hieu Hoang, Philipp Koehn, Tetsuo Kiso and Marcello Federico, International Workshop on Spoken Language Translation (IWSLT), 2011, pdf.
Agreement Constraints for Statistical Machine Translation into German, Philip Williams and Philipp Koehn, Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT), 2011, pdf, bib.
SampleRank Training for Phrase-Based Machine Translation, Barry Haddow, Abhishek Arun and Philipp Koehn, Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT), 2011, pdf, bib.
Findings of the 2011 Workshop on Statistical Machine Translation, Chris Callison-Burch, Philipp Koehn, Christof Monz and Omar Zaidan, Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT), 2011, pdf, bib.
Factored Translation Models, Philipp Koehn and Hieu Hoang, Chapter in Handbook of Natural Language Processing and Machine Translation, editors Olive, Christianson, and McCary, Springer, 2011.
Margin Infused Relaxed Algorithm for Moses, Eva Hasler, Barry Haddow and Philipp Koehn, The Prague Bulletin of Mathematical Linguistics, Volume 96, pages 69-78, October 2011, pdf.
What is a better translation? Reflections on six years of running evaluation campaigns, Philipp Koehn, Tralogy 2011, pdf.
Machine Translation, Philipp Koehn, Chapter in Multilingual Natural Language Processing Applications: From Theory to Practice, editors Imed Zitouni and Daniel M. Bikel, IBM Press, 2012.

2010

Statistical Machine Translation, Philipp Koehn, textbook, Cambridge University Press, January 2010, web, amazon.uk, amazon.com.
Enabling Monolingual Translators: Post-Editing vs. Options, Philipp Koehn, NAACL, 2010, pdf, bib.
An Experimental Management System, Philipp Koehn, The Prague Bulletin of Mathematical Linguistics, number 94, pages 87-96, September 2010, pdf.
Monte Carlo Techniques for Phrase-Based Translation, Abhishek Arun, Barry Haddow, Philipp Koehn, Adam Lopez, Chris Dyer and Miles Osborne, Machine Translation Journal, Volume 24, Number 2, pages 103-121, 2010.
Fast Approximate String Matching with Suffix Arrays and A* Parsing, Philipp Koehn and Jean Senellart, Meeting of the Association for Machine Translation of the Americas (AMTA), 2010, pdf.
Convergence of Translation Memory and Statistical Machine Translation, Philipp Koehn and Jean Senellart, AMTA Workshop on MT Research and the Translation Industry, 2010, pdf.
Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translation, Chris Callison-Burch, Philipp Koehn, Christof Monz, Kay Peterson, Mark Przybocki and Omar Zaidan, Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pdf, bib.
More Linguistic Annotation for Statistical Machine Translation, Philipp Koehn, Barry Haddow, Philip Williams and Hieu Hoang, Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pdf, bib.
Aiding Pronoun Translation with Co-Reference Resolution, Ronan Le Nagard and Philipp Koehn, Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pdf, bib.
A Unified Approach to Minimum Risk Training and Decoding, Abhishek Arun, Barry Haddow and Philipp Koehn, Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pdf, bib.
Improved Translation with Source Syntax Labels, Hieu Hoang and Philipp Koehn, Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010, pdf, bib.
Empirical Methods for Splitting Compound Words with Application to Machine Translation, Philipp Koehn, United States Patent 7711545, awarded 2010.

2009

A process study of computer-aided translation, Philipp Koehn, Machine Translation Journal, 2009, volume 23, number 4, pages 241-263, data, pdf.
Review of Cyril Goutte, Nicola Cancedda, Marc Dymetman, and George Foster (eds): Learning machine translation, Philipp Koehn, Machine Translation Journal, 2009, volume 23, number 4, pages 269-271.
A Uniform Framework for Phrase-Based, Hierarchical and Syntax-Based Machine Translation, Hieu Hoang, Philipp Koehn and Adam Lopez, International Workshop on Machine Translation (IWSLT), 2009, bib, pdf.
462 Machine Translation Systems for Europe, Philipp Koehn, Alexandra Birch and Ralf Steinberger, MT Summit XII, 2009, pdf.
Interactive Assistance to Human Translators using Statistical Machine Translation Methods, Philipp Koehn and Barry Haddow, MT Summit XII, 2009, pdf.
Selective addition of corpus-extracted phrasal lexical rules to a rule-based machine translation system, Loïc Dugast, Jean Senellart and Philipp Koehn, MT Summit XII, 2009, pdf.
Monte Carlo Inference and Maximization for Phrase-based Translation, Abhishek Arun, Chris Dyer, Barry Haddow, Phil Blunsom, Adam Lopez and Philipp Koehn, Conference on Computational Natural Language Learning, 2009, pdf, bib.
A Web-Based Interactive Computer Aided Translation Tool, Philipp Koehn, ACL Software demonstration, 2009, pdf, bib.
Word Lattices for Multi-Source Translation, Josh Schroeder, Trevor Cohn and Philipp Koehn, EACL 2009, pdf, bib.
Improving Mid-Range Re-Ordering using Templates of Factors, Hieu Hoang and Philipp Koehn, EACL 2009, pdf, bib.
Findings of the 2009 Workshop on Statistical Machine Translation, Chris Callison-Burch, Philipp Koehn, Christof Monz and Josh Schroeder, EACL Workshop on Statistical Machine Translation 2009, pdf.
Statistical Post Editing and Dictionary Extraction: Systran/Edinburgh submissions for ACL-WMT2009, Loïc Dugast, Jean Senellart and Philipp Koehn, EACL Workshop on Statistical Machine Translation 2009, pdf.
Edinburgh’s Submission to all Tracks of the WMT2009 Shared Task with Reordering and Speed Improvements to Moses, Philipp Koehn and Barry Haddow, EACL Workshop on Statistical Machine Translation 2009, pdf.
A Systematic Analysis of Translation Model Search Spaces, Michael Auli, Adam Lopez, Hieu Hoang and Philipp Koehn, EACL Workshop on Statistical Machine Translation 2009, pdf.
Statistical Machine Translation, Philipp Koehn and Kevin Knight, United States Patent 7624005, awarded 2009.
Constructing a translation lexicon from comparable, non-parallel corpora, Daniel Marcu, Kevin Knight, Dragos Munteanu, Philipp Koehn:, United States Patent 7620538, awarded 2009.

2008

Large and Diverse Language Models for Statistical Machine Translation, Holger Schwenk and Philipp Koehn, IJCNLP 2008, pdf.
Enriching Morphologically Poor Languages for Statistical Machine Translation, Eleftherios Avramidis and Philipp Koehn, ACL 2008, pdf.
Edinburgh University System Description for the 2008 NIST Machine Translation Evaluation, Philipp Koehn, Josh Schroeder and Miles Osborne, NIST MT Evaluation Meeting, pdf.
Design of the Moses Decoder for Statistical Machine Translation, Hieu Hoang and Philipp Koehn, ACL Workshop on Software engineering, testing, and quality assurance for NLP 2008, pdf.
Further Meta-Evaluation of Machine Translation, Chris Callison-Burch, Cameron Fordyce, Philipp Koehn, Christof Monz and Josh Schroeder, ACL Workshop on Statistical Machine Translation 2008, pdf.
Towards better Machine Translation Quality for the German-English Language Pairs, Philipp Koehn, Abhishek Arun and Hieu Hoang, ACL Workshop on Statistical Machine Translation 2008, pdf.
Can we Relearn an RBMT System?, Loic Dugastr, Jean Senellart and Philipp Koehn, ACL Workshop on Statistical Machine Translation 2008, pdf.
Predicting Success in Machine Translation, Alexandra Birch, Miles Osborne and Philipp Koehn, EMNLP 2008, pdf.
Phrase-Based Joint Probability Model for Statistical Machine Translation, Daniel Marcu, Kevin Knight, William Wong and Philipp Koehn, United States Patent 7454326, awarded 2008.

2007

Factored Translation Models, Philipp Koehn and Hieu Hoang, EMNLP 2007, pdf.
Chinese Syntactic Reordering for Statistical Machine Translation, Chao Wang, Michael Collins and Philipp Koehn, EMNLP 2007, pdf.
Moses: Open Source Toolkit for Statistical Machine Translation, Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, Evan Herbst, ACL 2007, demonstration session, pdf.
(Meta-) Evaluation of Machine Translation, Chris Callison-Burch, Cameron Fordyce, Philipp Koehn, Christof Monz and Josh Schroeder, ACL Workshop on Statistical Machine Translation 2007, pdf.
Experiments in Domain Adaptation for Statistical Machine Translation, Philipp Koehn and Josh Schroeder, ACL Workshop on Statistical Machine Translation 2007, pdf.
CCG Supertags in Factored Statistical Machine Translation, Alexandra Birch, Miles Osborne and Philipp Koehn, ACL Workshop on Statistical Machine Translation 2007, pdf.
Statistical Post-Edition on SYSTRAN Rule-Based Translation System, Loïc Dugast, Jean Senellart, Michel Simard and Philipp Koehn, ACL Workshop on Statistical Machine Translation 2007, pdf.
Online Learning Methods For Discriminative Training of Phrase Based Statistical Machine Translation, Abhishek Arun and Philipp Koehn, MT Summit XI, 2007.
The University of Edinburgh System Description for IWSLT 2007, Josh Schroeder and Philipp Koehn, IWSLT 2007, pdf.

2006

Improved Statistical Machine Translation Using Paraphrases, Chris Callison-Burch, Philipp Koehn and Miles Osborne, NAACL 2006, pdf.
Re-evaluating the Role of Bleu in Machine Translation Research, Chris Callison-Burch, Miles Osborne and Philipp Koehn, EACL 2006, pdf.
Statistical Machine Translation: the basic, the novel, and the speculative, Philipp Koehn, Tutorial at EACL 2006, slides, video: part 1, part 2.
Manual and Automatic Evaluation of Machine Translation between European Languages, Philipp Koehn and Christof Monz, NAACL 2006 Workshop on Statistical Machine Translation, pdf.
Constraining the Phrase-Based, Joint Probability Statistical Translation Model, Alexandra Birch, Chris Callison-Burch, Miles Osborne and Philipp Koehn, NAACL 2006 Workshop on Statistical Machine Translation, pdf.
Edinburgh System Description for the 2006 TC-STAR Spoken Language Translation Evaluation, Abhishek Arun, Amittai Axelrod, Philipp Koehn, TC-Star Evaluation Workshop, 2006.

2005

Clause Restructuring for Statistical Machine Translation Michael Collins, Philipp Koehn, and Ivona Kucerova, ACL 2005, pdf.
Shared Task: Statistical Machine Translation between European Languages, Philipp Koehn and Christof Monz ACL 2005 Workshop on Parallel Text, pdf.
Europarl: A Parallel Corpus for Statistical Machine Translation, Philipp Koehn, MT Summit 2005, pdf.
Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation, Philipp Koehn, Amittai Axelrod, Alexandra Birch Mayne, Chris Callison-Burch, Miles Osborne and David Talbot, International Workshop on Spoken Language Translation 2005, pdf.
Edinburgh System Description for the 2005 NIST MT Evaluation, Philipp Koehn, Amittai Axelrod, Alexandra Birch Mayne, Chris Callison-Burch, Miles Osborne, David Talbot, and Michael White, MT Eval Workshop 2005, pdf, slides.
Introduction to Statistical Machine Translation, Chris Callison-Burch and Philipp Koehn, European Summer School for Language and Logic (ESSLL) 2005, day1, 2, 3, 4, 5.

2004

Statistical Significance Tests for Machine Translation Evaluation, Philipp Koehn, EMNLP 2004, ps, pdf.
Pharaoh: a Beam Search Decoder for Phrase-Based Statistical Machine Translation Models, Philipp Koehn, AMTA 2004, pdf, ps, slides.
Challenges in Statistical Machine Translation, Philipp Koehn, Talk given at PARC, Google, ISI, MITRE, BBN, Univ. of Montreal, 2004, slides.
The Foundation for Statistical Machine Translation at MIT, Philipp Koehn, Talk given at DARPA/TIDES MT Evaluation Workshop, 2004, slides.
What's New in Statistical Machine Translation, Kevin Knight and Philipp Koehn, Tutorial at HLT/NAACL 2004.
Introduction to Statistical Machine Translation, Philipp Koehn and Kevin Knight, Tutorial at AMTA 2004.
Automatic Evaluation, Philipp Koehn, Panel talk at the AMTA 2004 panel on Machine Translation Evaluation, slides.

2003

Noun Phrase Translation, Philipp Koehn, PhD thesis, University of Southern California, 2003, ps (official format, 182 pages), ps (readable format, 118 pages).
Advances in Statistical Machine Translation: Phrases, Noun Phrases and Beyond, Philipp Koehn, Talk given at ISI, JHU, UMD, MITRE, MIT, IBM, Columbia, AT&T, 2003, slides.
Feature-Rich Statistical Translation of Noun Phrases, Philipp Koehn and Kevin Knight, ACL 2003, ps, pdf, abstract.
Statistical Phrase-Based Translation, Philipp Koehn, Franz Josef Och, and Daniel Marcu, HLT/NAACL 2003, ps, pdf, slides, abstract.
Empirical Methods for Compound Splitting, Philipp Koehn and Kevin Knight, EACL 2003, ps, pdf, abstract.
What's New in Statistical Machine Translation, Kevin Knight and Philipp Koehn, Tutorial at HLT/NAACL 2003, slides.
Statistical Machine Translation, Kevin Knight and Philipp Koehn, Tutorial at MT Summit 2003.
Desparately Seeking Cebuano, 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, NAACL-HLT 2003.

2002

Learning a Translation Lexicon from Monolingual Corpora, Philipp Koehn and Kevin Knight, ACL 2002, Workshop on Unsupervised Lexical Acquisition, ps, pdf.
Combining Multiclass Maximum Entropy Text Classifiers with Neural Network Voting, Philipp Koehn, PorTAL 2002, ps, pdf.
Translation with Scarce Bilingual Resources, Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, and Kenji Yamada, Machine Translation 17: 1-17, 2002, ps, pdf.
ChunkMT: Statistical Machine Translation with Richer Linguistic Knowledge, Philipp Koehn and Kevin Knight, Draft, Unpublished, ps, pdf.

2001

Knowledge Sources for Word-Level Translation Models, Philipp Koehn and Kevin Knight, EMNLP 2001, ps, pdf, abstract.

2000

Estimating Word Translation Probabilities from Unrelated Monolingual Corpora Using the EM Algorithm, Philipp Koehn and Kevin Knight, AAAI 2000, ps, pdf, abstract.
Translating with Scarce Resources, Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, and Kenji Yamada, AAAI 2000, ps, pdf, abstract.
Improving Intonational Phrasing with Syntactic Information, Philipp Koehn, Steven Abney, Julia Hirschberg, and Michael Collins, ICASSP 2000, ps, pdf, abstract.

Earlier

Statistische und modellbasierte Lernverfahren zur Erweiterung von Unifikationsgrammatiken, Philipp Koehn, 1996, Diplom thesis at the University of Erlangen-Nuremberg, Germany. ps, pdf, code, German abstract, English abstract.
Genetic Encoding Strategies for Neural Networks, Philipp Koehn, IPMU 1996, ps, pdf, abstract.
Combining Genetic Algorithms and Neural Networks, Philipp Koehn, 1994, Master Thesis at the University of Tennessee at Knoxville, USA. ps, pdf, code, abstract.

links

Do not spell my name like this: Phillip Koehn, Philip Koehn, Phillipp Koehn, Phillip Köhn, Philip Köhn, Phillipp Köhn, Phillip Kohn, Philip Kohn, Phillipp Kohn, Philipp Kohn. My real name is Philipp Köhn, but the preferred spelling is Philipp Koehn.