Ulrich Germann
Senior Researcher in Machine Translation

School of Informatics
University of Edinburgh

Email: ugermann@inf.ed.ac.uk
I'm a Senior Researcher in Statistical and Neural Machine Translation at the University of Edinburgh's School of Informatics.

Current Projects

European Language Grid (2019–2021)
Bergamot (2019–2021)

Past Projects

Scalable Understanding of Multimedia (2016–2018)
ModernMT (2015–2017)
MateCat (2012–2014)
CasMaCat (2012–2014)
ACCEPT (2012–2014)
Quality Translation 21 (2015–2016)

Publications

Software

2012– I've been an active contributor to the open-source Moses Machine Translation System since 2012.
2007 Yawat is a web-based tool for manual word alignment. It's now on github.
2002 ElectAssist is a toolkit for the administration of online elections. I wrote it for low-stakes elections for the NAACL way back when. It's old and was never secure (just made sure everyone voted only once), and there are better alternatives now.
2000 ISI ReWrite Decoder (with Daniel Marcu) was, to the best of my knowledge, the first publicly available decoder for machine translation. We were not allowed to release it as open-source; so unfortunately only the binary is available.

Conference and Workshop Papers

2017 A. V. Miceli Barone, B. Haddow, U. Germann, and R. Sennrich. 2017. “Regularization Techniques for Fine-tuning in Neural Machine Translation.” Proceedings of the Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.
2017 R. Sennrich, A. Birch, A. Currey, U. Germann, B. Haddow, K. Heafield, A. V. Miceli Barone, and P. Williams. 2017. “The University of Edinburgh's Neural MT Systems for WMT17.” Second Conference on Machine Translation (WMT17), Copenhagen, Denmark.
2017 N. Bertoldi, R. Cattoni, M. Cettolo, A. Farajian, M. Federico, D. Caroselli, L. Mastorstefano, A. Rossi, M. Trombetti, U. Germann, and D. Madl. 2017. “MMT: New Open Source MT for the Translation Industry.” 20th Annual Conference of the European Association for Machine Translation, Prague, Czech Republic.
2017 R. Liepins, U. Germann, G. Barzdins, A. Birch, S. Renals, S. Weber, P. van der Kreeft, H. Bourlard, J. Prieto, O. Klejch, P. Bell, A. Lazaridis, A. Mendes, S. Riedel, M. S. C. Almeida, P. Balage, S. B. Cohen, T. Dwojak, P. N. Garner, A. Giefer, M. Junczys-Dowmunt, H. Imran, D. Nogueira, A. Ali, S. Miranda, A. Popescu-Belis, L. Miculicich Werlen, N. Papasarantopoulos, A. Obamuyide, C. Jones, F. Dalvi, A. Vlachos, Y. Wang, S. Tong, R. Sennrich, N. Pappas, S. Narayan, M. Damonte, N. Durrani, S. Khurana, A. Abdelali, H. Sajjad, S. Vogel, D. Sheppey, C. Hernon, and J. Mitchell. 2017. “The SUMMA Platform Prototype.” Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp. 116–119, Valencia, Spain.
2016 U. Germann. 2016. “Bilingual Document Alignment with Latent Semantic Indexing.” Proceedings of the First Conference on Machine Translation, pp. 692–696, Berlin, Germany.
2014 U. Germann. 2014. “Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario.” AMTA 2014 Workshop on Interactive and Adaptive Machine Translation, pp. 20–31, Vancouver, BC, Canada.
2014 V. Alabau, C. Buck, M. Carl, F. Casacuberta, M. García-Martínez, U. Germann, J. González-Rubio, R. Hill, P. Koehn, L. Leiva, B. Mesa-Lao, D. Ortiz-Martínez, H. Saint-Amand, G. Sanchis Trilles, and C. Tsoukala. 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, pp. 25–28, Gothenburg, Sweden.
2014 M. Federico, N. Bertoldi, M. Cettolo, M. Negri, M. Turchi, M. Trombetti, A. Cattelan, A. Farina, D. Lupinetti, A. Martines, A. Massidda, H. Schwenk, L. Barrault, F. Blain, P. Koehn, C. Buck, and U. Germann. 2014. “The MateCat Tool.” Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations, pp. 129–132, Dublin, Ireland.
2014 P. Koehn and U. Germann. 2014. “The Impact of Machine Translation Quality on Human Post-Editing.” Proceedings of the EACL 2014 Workshop on Humans and Computer-assisted Translation, pp. 38–46, Gothenburg, Sweden.
2013 A. Birch, B. Haddow, U. Germann, M. Nadejde, C. Buck, and P. Koehn. 2013. “The Feasibility of HMEANT as a Human MT Evaluation Metric.” Proceedings of the Eighth Workshop on Statistical Machine Translation, pp. 52–61, Sofia, Bulgaria.
2013 P. Bouillon, J. Gerlach, U. Germann, B. Haddow, and M. Rayner. 2013. “Two Approaches to Correcting Homophone Confusions in a Hybrid Machine Translation System.” Proceedings of the Second Workshop on Hybrid Approaches to Translation, pp. 109–116, Sofia, Bulgaria.
2012 U. Germann. 2012. “Syntax-aware Phrase-based Statistical Machine Translation: System Description.” Proceedings of the Seventh Workshop on Statistical Machine Translation, pp. 292–297, Montréal, Canada.
2010 S. Larkin, B. Chen, G. Foster, U. Germann, E. Joanis, H. Johnson, and R. Kuhn. 2010. “Lessons from NRC's Portage System at WMT 2010.” Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pp. 127–132, Uppsala, Sweden.
2009 U. Germann, E. Joanis, and S. Larkin. 2009. “Tightly Packed Tries: How to Fit Large Models into Memory, and Make them Load Fast, Too.” Proceedings of the Workshop on Software Engineering, Testing, and Quality Assurance for Natural Language Processing (SETQA-NLP 2009), pp. 31–39, Boulder, Colorado.
2009 P. Paul, S. Larkin, U. Germann, E. Joanis, and R. Kuhn. 2009. “\itshape PortageLive: Delivering Machine Translation Technology via Virtualization.” Technology Showcase at the Machine Translation Summit XII, Ottawa, ON, Canada.
2008 U. Germann. 2008. “Yawat: Yet Another Word Alignment Tool.” Proceedings of the ACL-08: HLT Demo Session, pp. 20–23, Columbus, Ohio.
2007 U. Germann. 2007. “Two Tools for Creating and Visualizing Sub-sentential Alignments of Parallel Text.” Proceedings of the Linguistic Annotation Workshop, pp. 121–124, Prague, Czech Republic.
2003 U. Germann. 2003. “Greedy Decoding for Statistical Machine Translation in Almost Linear Time.” Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp. 72–79, Edmonton, AB, Canada.
2003 E. Hovy, A. Philpot, J. Klavans, U. Germann, P. Davis, and S. Popper. 2003. “Extending Metadata Definitions by Automatically Extracting and Organizing Glossary Definitions.” Proceedings of the 2003 Annual National Conference on Digital Government Research, pp. 1–6
2001 U. Germann. 2001. “Building a Statistical Machine Translation System from Scratch: How Much Bang for the Buck Can We Expect?” ACL 2001 Workshop on Data-driven Machine Translation, pp. 63–70, Toulouse, France.
2001 U. Germann, M. Jahr, K. Knight, D. Marcu, and K. Yamada. 2001. “Fast Decoding and Optimal Decoding for Machine Translation.” Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, pp. 228–235, Toulouse, France.
2000 Y. Al-Onaizan, U. Germann, U. Hermjakob, K. Knight, P. Koehn, D. Marcu, and K. Yamada. 2000. “Translating with Scarce Resources.” 17th National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence (AAAI-IAAI), pp. 672–678, Austin, TX, USA.
1999 U. Germann. 1999. “A Deterministic Dependency Parser for Japanese.” Proceedings of the Machine Translation Summit VIII, pp. 547–555, Singapore.
1998 U. Germann. 1998. “Making Semantic Interpretation Parser-independent.” Machine Translation and the Information Soup: Proceedings of the Third Conference of the Association for Machine Translation in the Americas (AMTA '98), pp. 286–299, Langhorne, PA, USA.
1998 U. Germann. 1998. “Visualization of Protocols of the Parsing and Semantic Interpretation Steps in a Machine Translation System.” COLING-ACL '98 Workshop on Content Visualization and Intermedia Representations, pp. 83–90, Montréal, QC, Canada.

Journal Articles

2015 U. Germann. 2015. “Sampling Phrase Tables for the Moses Statistical Machine Translation System.” The Prague Bulletin of Mathematical Linguistics, pp. 39–50.
2014 G. Sanchis-Trilles, V. Alabau, C. Buck, M. Carl, F. Casacuberta, M. García-Martínez, U. Germann, J. González-Rubio, R. Hill, P. Koehn, L. Leiva, B. Mesa-Lao, D. Ortiz-Martínez, H. Saint-Amand, C. Tsoukala, and E. Vidal. 2014. “Interactive Translation Prediction versus Conventional Post-editing in Practice: a Study with the CasMaCat Workbench.” Machine Translation 28 (3-4), pp. 217–235.
2013 U. Germann. 2013. “Makefiles for Moses.” The Prague Bulletin of Mathematical Linguistics 100, pp. 9–18.
2004 U. Germann, M. Jahr, K. Knight, D. Marcu, and K. Yamada. 2004. “Fast Decoding and Optimal Decoding for Machine Translation.” Artificial Intelligence  154 (1--2), pp. 127–143.
2003 A. Leuski, C. Lin, L. Zhou, U. Germann, F. J. Och, and E. Hovy. 2003. “Cross-lingual C*ST*RD: English Access to Hindi Information.” ACM Transactions on Asian Language Information Processing (TALIP) 2 (3), pp. 245–269.
2002 Y. Al-Onaizan, U. Germann, U. Hermjakob, K. Knight, P. Koehn, D. Marcu, and K. Yamada. 2002. “Translation with Scarce Bilingual Resources.” Machine Translation 17 (1), pp. 1–17.

Book Chapters

2016 S. Läubli and U. Germann. 2016. “Statistical Modelling and Automatic Tagging of Human Translation Processes.” in M. Carl, S. Bangalore, and M. Schaeffer: New Directions in Empirical Translation Process Research, Springer.
1996 U. Germann. 1996. “C-Tests automatisch erstellen --- mit Word für Windows 6.0.” in R. Grotjahn (Ed.): Der C-Test. Theoretische Grundlagen und praktische Anwendungen, pp. 419–443, Bochum, Germany: Brockmeyer
1994 U. Germann and R. Grotjahn. 1994. “Das Lösen von C-Tests auf dem Computer: Eine Pilotuntersuchung zu den Bearbeitungsprozessen.” in R. Grotjahn (Ed.): Der C-Test. Theoretische Grundlagen und praktische Anwendungen, pp. 279–304, Bochum, Germany: Brockmeyer

Technical Reports and other non-refereed Publications

2006 U. Germann. 2006. An Iterative Approach to Pitch-marking of Speech Signals without Electroglottographic Data.. Technical Report. University of Toronto. Toronto, ON, Canada.
1996 U. Germann. 1996. Die Übersetzbarkeit von Wörterbüchern des Cobuild-Typs in HPSG-Lexika: Eine Untersuchung anhand des Englischen und Japanischen.. Master's Thesis. Ruhr-Universität Bochum. Bochum, Germany.