Koehn, Philipp

Professor
Department Of Computer Science
Personal Website

Hackerman 226
3400 North Charles St
(410) 516-3427
phi@jhu.edu

Jump to:

News

About

Education
  • Ph.D. 2003, University of Southern California
  • Other Master's Degree (Diplom, Computer Science) 1996, Universität Erlangen-Nürnberg
  • M.S. 1994, University of Tennessee,
Experience
  • January 1, 2004 - Present:  Professor, University of Edinburgh
Research Areas
  • Machine Translation, Big Data Natural Language Processing
Awards
  • 2015:  Award of Honor
  • 2013:  Finalist, European Inventor Award
Presentations
  • "Progress in Statistical and Neural Machine Translation", Booking.com Seminar.  Amsterdam, The Netherlands.  January 27, 2017
  • "Introduction to Neural Machine Translation", Omniscien Technology Webinar.  Online.  January 24, 2017
  • "The State of Neural Machine Translation", Webinar Omniscien Technology.  Online.  November 24, 2016
  • "Morphology in Low Resource Machine Translation", Workshop on Semitic Languages.  Austin, Texas.  November 1, 2016
  • "MT Marathons, Open Source, and Collaborative Research in MT", AMTA Conference.  Austin, Texas.  October 29, 2016
  • "CASMACAT - Advancing computer aided translation beyond post-editing", Translating Europe Forum.  Brussels, Belgium.  October 28, 2016
  • "Computer Aided Translation. With Neurons", Machine Translation Marathon.  Prague, Czech Republic.  September 16, 2016
  • "Machine Translation as Sequence Prediction", 6th Lisbon Machine Learning School.  Lisbon, Portugal.  July 23, 2016
  • "Advances in Computer Aided Translation Beyond Post-Editing", Machine Translation Summit.  Miami, FL.  October 31, 2015
  • "Johns Hopkins University: Syntax-Based System", NIST Open Machine Translation Evaluation.  Alexandria, VA.  June 25, 2015
  • "Machine Translation: Going Deep", Workshop on Syntax, Semantics and Structure in Statistical Translation.  Denver, CO.  June 4, 2015
  • "Machine Translation and the Translator", International Annual Meeting on Computer-Assisted Translation and Terminology (JIAMCATT).  New York, NY.  April 8, 2015
  • "Challenges in Machine Translation", Invited Talk.  Moscow.  November 28, 2014
  • "Tutorial Syntax-Based Statistical Machine Translation", Conference on Empirical Methods in Natural Language Processing.  Qatar.  October 29, 2014
  • "Recent Research in Machine Translation", Invited Talk.  Baltimore.  July 28, 2014
  • "Recent Research in Machine Translation", Invited Talk.  New York.  July 3, 2014
  • "Machine Translation and Human Translation", Invited Talk.  Edinburgh.  March 22, 2014

Publications

Journal Articles
  • Durrani, N., Schmid, H., Fraser, A., Koehn, P., Schütze, H. (2015).  The Operation Sequence Model – Combining N-Gram-Based and Phrase-Based Statistical Machine Translation.  Computational Linguistics.  41(2).
  • Sanchis-Trilles, G., Alabau, V., Buck, C., Carl, M., Casacuberta, F., García-Martínez, M., Germann, U., JesúsGonzález-Rubio., Hill, R. L., Koehn, P., Leiva, L. A., Mesa-Lao, B., Ortiz-Martínez, D., Saint-Amand, H., Tsoukala, C. (2014).  Interactive translation prediction versus conventional post-editing in practice: a study with the CasMaCat workbench.  Machine Translation.  28(3-4).  217-235.
Books
  • Williams, P., Sennrich, R., Post, M., Koehn, P. (2016).  Syntax-based Statistical Machine Translation, Philip Williams, Rico Sennrich, Philipp Koehn, and Matt Post, Synthesis Lectures on Human Language Technologies, , 2016.  Morgan and Claypool Publishers.  190.
Conference Proceedings
  • Nadejde, M., Birch, A., Koehn, P. (2016).  A Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation.  Proceedings of the International Workshop on Spoken Language Translation (IWSLT).
  • Sanchez-Torron, M., Koehn, P. (2016).  Machine Translation Quality and Post-Editor Productivity.  Proceedings of the Conference of the Association for Machine Translation in the Americas (AMTA).
  • Knowles, R., Koehn, P. (2016).  Neural Interactive Translation Prediction.  Proceedings of the Conference of the Association for Machine Translation in the Americas (AMTA).
  • Bojar, O., Federmann, C., Haddow, B., Koehn, P., Post, M., Specia, L. (2016).  Ten Years of WMT Evaluation Campaigns: Lessons Learnt.  Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16).
  • Gujral, B., Khayrallah, H., Koehn, P. (2016).  Translation of Unknown Words in Low Resource Languages.  Proceedings of the Conference of the Association for Machine Translation in the Americas (AMTA).
  • Buck, C., Koehn, P. (2016).  UEdin participation in the 1st Translation Memory Cleaning Shared Task.  Proceedings of the 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM).
  • Knowles, R., Renduchintala, A., Koehn, P., Eisner, J. (2016).  Analyzing Learner Understanding of Novel L2 Vocabulary.  Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning.  Association for Computational Linguistics.  126–135.
  • Renduchintala, A., Knowles, R., Koehn, P., Eisner, J. (2016).  Creating Interactive Macaronic Interfaces for Language Learning.  Proceedings of ACL-2016 System Demonstrations.  Association for Computational Linguistics.  133–138.
  • Bojar, O., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huck, M., Jimeno Yepes, A., Koehn, P., Logacheva, V., Monz, C., Negri, M., Neveol, A., Neves, M., Popel, M., Post, M., Rubino, R., Scarton, C., Specia, L., Turchi, M., Verspoor, K., Zampieri, M. (2016).  Findings of the 2016 Conference on Machine Translation.  Proceedings of the First Conference on Machine Translation.  Association for Computational Linguistics.  131–198.
  • Buck, C., Koehn, P. (2016).  Quick and Reliable Document Alignment via TF/IDF-weighted Cosine Distance.  Proceedings of the First Conference on Machine Translation.  Association for Computational Linguistics.  672–678.
  • Ding, S., Duh, K., Khayrallah, H., Koehn, P., Post, M. (2016).  The JHU Machine Translation Systems for WMT 2016.  Proceedings of the First Conference on Machine Translation.  Association for Computational Linguistics.  272–280.
  • Renduchintala, A., Knowles, R., Koehn, P., Eisner, J. (2016).  User Modeling in Language Learning with Macaronic Texts.  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).  Association for Computational Linguistics.  1859–1869.
  • Koehn, P. (2015).  Computer Aided Translation: Advances and Challenges.  Machine Translation Summit.
  • Williams, P., Sennrich, R., Nadejde, M., Huck, M., Koehn, P. (2015).  Edinburgh’s Syntax-Based Systems at WMT 2015.  Proceedings of the Tenth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  199–209.
  • Bojar, O., Chatterjee, R., Federmann, C., Haddow, B., Huck, M., Hokamp, C., Koehn, P., Logacheva, V., Monz, C., Negri, M., Post, M., Scarton, C., Specia, L., Turchi, M. (2015).  Findings of the 2015 Workshop on Statistical Machine Translation.  Proceedings of the Tenth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  1–46.
  • Stanojevic, M., Kamran, A., Koehn, P., Bojar, O. (2015).  Results of the WMT15 Metrics Shared Task.  Proceedings of the Tenth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  256–273.
  • Haddow, B., Huck, M., Birch, A., Bogoychev, N., Koehn, P. (2015).  The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT2015.  Proceedings of the Tenth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  126–133.
  • Freitag, M., Wübker, J., Peitz, S., Ney, H., Huck, M., Birch, A., Durrani, N., Koehn, P., Mediani, M., Slawik, I., Niehues, J., Cho, E., Waibel, A., Bertoldi, N., Cettolo, M., Federico, M. (2014).  Combined Spoken Language Translation.  Proceedings of the International Workshop on Spoken Language Translation (IWSLT).  57–64.
  • Hasler, E., Haddow, B., Koehn, P. (2014).  Combining domain and topic adaptation for SMT.  Proceedings of the Eleventh Conference of the Association for Machine Translation in the Americas (AMTA).  1.  139-151.
  • Birch, A., Huck, M., Durrani, N., Bogoychev, N., Koehn, P. (2014).  Edinburgh SLT and MT System Description for the IWSLT 2014 Evaluation.  Proceedings of the International Workshop on Spoken Language Translation (IWSLT).  49–56.
  • Durrani, N., Koehn, P. (2014).  Improving machine translation via triangulation and transliteration.  Proceedings of 17th Annual conference of the European Association for Machine Translation.  71-78.
  • Huck, M., Hoang, H., Koehn, P. (2014).  Preference Grammars and Soft Syntactic Constraints for GHKM Syntax-based Statistical Machine Translation.  Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation.  Association for Computational Linguistics.  148–156.
  • Durrani, N., Koehn, P., Schmid, H., Fraser, A. (2014).  Investigating the Usefulness of Generalized Word Representations in SMT.  Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers.  Dublin City University and Association for Computational Linguistics.  421–432.
  • Federico, M., Bertoldi, N., Cettolo, M., Negri, M., Turchi, M., Trombetti, M., Cattelan, A., Farina, A., Lupinetti, D., Martines, A., Massidda, A., Schwenk, H., Barrault, L., Blain, F., Koehn, P., Buck, C., Germann, U. (2014).  The MATECAT Tool.  Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations.  Dublin City University and Association for Computational Linguistics.  129–132.
  • Huck, M., Hoang, H., Koehn, P. (2014).  Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  486–498.
  • Hasler, E., Haddow, B., Koehn, P. (2014).  Dynamic Topic Adaptation for SMT using Distributional Profiles.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  445–456.
  • Durrani, N., Haddow, B., Koehn, P., Heafield, K. (2014).  Edinburgh’s Phrase-based Machine Translation Systems for WMT-14.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  97–104.
  • Williams, P., Sennrich, R., Nadejde, M., Huck, M., Hasler, E., Koehn, P. (2014).  Edinburgh’s Syntax-Based Systems at WMT 2014.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  207–214.
  • Freitag, M., Peitz, S., Wuebker, J., Ney, H., Huck, M., Sennrich, R., Durrani, N., Nadejde, M., Williams, P., Koehn, P., Herrmann, T., Cho, E., Waibel, A. (2014).  EU-BRIDGE MT: Combined Machine Translation.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  105–113.
  • Bojar, O., Buck, C., Federmann, C., Haddow, B., Koehn, P., Leveling, J., Monz, C., Pecina, P., Post, M., Saint-Amand, H., Soricut, R., Specia, L., Tamchyna, A. (2014).  Findings of the 2014 Workshop on Statistical Machine Translation.  Proceedings of the Ninth Workshop on Statistical Machine Translation.  Association for Computational Linguistics.  12–58.
  • Koehn, P., Tsoukala, C., Saint-Amand, H. (2014).  Refinements to Interactive Translation Prediction Based on Search Graphs.  Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).  Association for Computational Linguistics.  574–578.
  • Alabau, V., Buck, C., Carl, M., Casacuberta, F., García-Martínez, M., Germann, U., González-Rubio, J., Hill, R., Koehn, P., Leiva, L., Mesa-Lao, B., Ortiz-Martínez, D., Saint-Amand, H., Sanchis Trilles, G., Tsoukala, C. (2014).  CASMACAT: A Computer-assisted Translation Workbench.  Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics.  Association for Computational Linguistics.  25–28.
  • Hasler, E., Blunsom, P., Koehn, P., Haddow, B. (2014).  Dynamic Topic Adaptation for Phrase-based MT.  Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics.  Association for Computational Linguistics.  328–337.
  • Durrani, N., Sajjad, H., Hoang, H., Koehn, P. (2014).  Integrating an Unsupervised Transliteration Model into Statistical Machine Translation.  Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers.  Association for Computational Linguistics.  148–153.
  • Koehn, P., Germann, U. (2014).  The Impact of Machine Translation Quality on Human Post-Editing.  Proceedings of the EACL 2014 Workshop on Humans and Computer-assisted Translation.  Association for Computational Linguistics.  38–46.
  • Williams, P., Koehn, P. (2014).  Using Feature Structures to Improve Verb Translation in English-to-German Statistical MT.  Proceedings of the 3rd Workshop on Hybrid Approaches to Machine Translation (HyTra).  Association for Computational Linguistics.  21–29.
Back to top