Barry Haddow

Barry Haddow on Stuc a'Chroin    

Contact information:

School of Informatics
The Informatics Forum
10 Crichton Street
Edinburgh EH8 9AB
email: bhaddow at inf dot ed dot ac dot uk

About Me

I am a research fellow in the ILCC at the University of Edinburgh.

Projects

Feb 2012 - Jan 2015 MosesCore
Supporting open source machine translation through MT marathons, shared tasks and workshops, and continued Moses development, as well as industrial outreach.

Jan 2012 - Dec 2014 Accept
Improving the translation of user-generated content through pre- and post-editing, and advances in the underlying machine translation.

Jan 2011 - Dec 2013 MLTMLV
Automatic ranslation from standard German into dialects, particularly Viennese.

Feb 2009 - Feb 2012 EUROMATRIXPLUS
Continuing the work of Euromatrix, but focussing on bringing translation to the user, with interactive tools, translation of news stories, and improvements to the core system.

Jan 2008 - Feb 2009 EUROMATRIX
This project is in statistical machine translation, working on tools and evaluations for the translation of all EU language pairs.

Sep 2005 - Dec 2007 TXM
A biomedical information extraction project aiming to produce natural language processing tools to assist curators in their work.

Publications

[1] Eva Hasler, Barry Haddow, and Philipp Koehn. Dynamic Topic Adaptation for SMT using Distributional Profiles. In Proceedings of the Ninth Workshop on Statistical Machine Translation, Baltimore, USA, June 2014. Association for Computational Linguistics. [ bib ]
[2] Nadir Durrani, Barry Haddow, Kenneth Heafield, and Philipp Koehn. Edinburgh's Phrase-based Machine Translation Systems for WMT-14. In Proceedings of the Ninth Workshop on Statistical Machine Translation, Baltimore, USA, June 2014. Association for Computational Linguistics. [ bib ]
[3] Ondřej Bojar, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia, and Ales Tamchyna. Findings of the 2014 Workshop on Statistical Machine Translation. In Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 12-58, Baltimore, USA, June 2014. Association for Computational Linguistics. [ bib ]
[4] Eva Hasler, Phil Blunsom, Philipp Koehn, and Barry Haddow. Dynamic Topic Adaptation for Phrase-based MT. In Proceedings of EACL, 2014. [ bib | .pdf ]
[5] Friedrich Neubarth, Barry Haddow, Adolfo Hernandez, and Harald Trost. A hybrid approach to statistical machine translation between standard and dialectal varieties. In Proceedings of the Sixth Language and Technology Conference, 2013. [ bib | .pdf ]
[6] Barry Haddow, Adolfo Hernandez, Friedrich Neubarth, and Harald Trost. Corpus development for machine translation between standard and dialectal varieties. In Proceedings of Workshop on Adaptation of language resources and tools for closely related languages and language variants, 2013. [ bib | .pdf ]
[7] Alexandra Birch, Barry Haddow, Ulrich Germann, Maria Nadejde, Christian Buck, and Philipp Koehn. The feasibility of HMEANT as a human MT evaluation metric. In Proceedings of the Eighth Workshop on Statistical Machine Translation, pages 52-61, Sofia, Bulgaria, August 2013. Association for Computational Linguistics. [ bib | .pdf ]
[8] Ondřej Bojar, Christian Buck, Chris Callison-Burch, Christian Federmann, Barry Haddow, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut, and Lucia Specia. Findings of the 2013 Workshop on Statistical Machine Translation. In Proceedings of the Eighth Workshop on Statistical Machine Translation, pages 1-44, Sofia, Bulgaria, August 2013. Association for Computational Linguistics. [ bib | .pdf ]
[9] Nadir Durrani, Barry Haddow, Kenneth Heafield, and Philipp Koehn. Edinburgh's machine translation systems for European language pairs. In Proceedings of the Eighth Workshop on Statistical Machine Translation, pages 114-121, Sofia, Bulgaria, August 2013. Association for Computational Linguistics. [ bib | .pdf ]
[10] Pierrette Bouillon, Johanna Gerlach, Ulrich German, Barry Haddow, and Manny Rayner. Two Approaches to Correcting Homophone Confusions in a Hybrid Machine Translation System. In Proceedings of Second Workshop on Hybrid Approaches to Translation (HyTra), 2013. [ bib | .pdf ]
[11] Barry Haddow. Applying pairwise ranked optimisation to improve the interpolation of translation models. In Proceedings of NAACL, 2013. [ bib | .pdf ]
[12] Eva Hasler, Barry Haddow, and Philipp Koehn. Sparse lexicalised features and topic adaptation for SMT. In Proceedings of IWSLT, 2012. [ bib | .pdf ]
[13] Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals, and Pawel Swietojanski. The UEDIN systems for the IWSLT 2012 evaluation. In Proceedings of IWSLT, 2012. [ bib | .pdf ]
[14] Manny Rayner, Pierrette Bouillon, and Barry Haddow. Using source-language transformations to address register mismatches in SMT. In Proceedings of AMTA, 2012. [ bib | .pdf ]
[15] Philipp Koehn and Barry Haddow. Interpolated backoff for factored translation models. In Proceedings of AMTA, 2012. [ bib | .pdf ]
[16] Barry Haddow and Philipp Koehn. Analysing the effect of out-of-domain data on SMT systems. In Proceedings of the Seventh Workshop on Statistical Machine Translation, Montreal, Canada, June 2012. Association for Computational Linguistics. [ bib | .pdf ]
[17] Philipp Koehn and Barry Haddow. Towards effective use of training data in statistical machine translation. In Proceedings of the Seventh Workshop on Statistical Machine Translation, Montreal, Canada, June 2012. Association for Computational Linguistics. [ bib | .pdf ]
[18] Eva Hasler, Barry Haddow, and Philipp Koehn. Margin infused relaxed algorithm for moses. Prague Bulletin of Mathematical Linguistics, No. 96:69-78, 2011. [ bib | .pdf ]
[19] Barry Haddow, Abhishek Arun, and Philipp Koehn. Samplerank training for phrase-based machine translation. In Proceedings of the Sixth Workshop on Statistical Machine Translation, Edinburgh, Scotland, July 2011. Association for Computational Linguistics. (Contains minor corrections to published version). [ bib | .pdf ]
[20] Philipp Koehn, Barry Haddow, Philip Williams, and Hieu Hoang. More linguistic annotation for statistical machine translation. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 115-120, Uppsala, Sweden, July 2010. Association for Computational Linguistics. [ bib | .pdf ]
[21] Abhishek Arun, Barry Haddow, and Philipp Koehn. A unified approach to minimum risk training and decoding. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 365-374, Uppsala, Sweden, July 2010. Association for Computational Linguistics. [ bib | slides | .pdf ]
[22] Abhishek Arun, Barry Haddow, Philipp Koehn, Adam Lopez, Chris Dyer, and Phil Blunsom. Monte carlo techniques for phrase-based translation. Machine Translation, 2010. [ bib | DOI | .pdf ]
[23] Barry Haddow. Adding multi-threaded decoding to moses. Prague Bulletin of Mathematical Linguistics, No. 93:57-66, 2010. [ bib | slides | .pdf ]
[24] Philipp Koehn and Barry Haddow. Interactive assistance to human translators using statistical machine translation methods. In Proceedings of MT Summit XII, Ottawa, Canada, 2009. [ bib ]
[25] Abhishek Arun, Chris Dyer, Barry Haddow, Phil Blunsom, Adam Lopez, and Philipp Koehn. Monte carlo inference and maximization for phrase-based translation. In Proceedings of the Conference on Natural Language Learning, Boulder, USA, June 2009. Association for Computational Linguistics. [ bib | .pdf ]
[26] Philipp Koehn and Barry Haddow. Edinburgh's submission to all tracks of the WMT 2009 shared task with reordering and speed improvements to Moses. In Proceedings of the Fourth Workshop on Statistical Machine Translation, pages 160-164, Athens, Greece, March 2009. Association for Computational Linguistics. [ bib | .pdf ]
[27] Nicola Bertoldi, Barry Haddow, and Jean-Baptiste Fouet. Improved minimum error rate training in moses. Prague Bulletin of Mathematical Linguistics, No. 91:7-16, 2009. [ bib | slides | .pdf ]
[28] Barry Haddow. Using automated feature optimisation to create an adaptable relation extraction system. In Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing, pages 19-27, Columbus, Ohio, June 2008. Association for Computational Linguistics. [ bib | .pdf ]
[29] Bea Alex, Claire Grover, Barry Haddow, Mijail Kabadjov, Ewan Klein, Michael Matthews, Stuart Roebuck, Richard Tobin, and Xinglong Wang. The ITI TXM Corpora: Tissue Expressions and Protein-Protein Interactions. In Proceedings of Workshop on Building and evaluating resources for biomedical text mining, LREC 2008, Marrakesh, Morocco, 2008. [ bib | .pdf ]
[30] Barry Haddow and Beatrice Alex. Exploiting multiply annotated corpora in biomedical information extraction tasks. In Proceedings of LREC, Marrakesh, Morocco, 2008. [ bib | .pdf ]
[31] Beatrice Alex, Claire Grover, Barry Haddow, Mijail Kabadjov, Ewan Klein, Michael Matthews, Richard Tobin, and Xinglong Wang. Automating curation using a natural language processing pipeline. Genome Biology, 9(Suppl 2):S10, 2008. [ bib | DOI | http ]
[32] Larry Smith et al. Overview of biocreative ii gene mention recognition. Genome Biology, 9(Suppl 2):S2, 2008. [ bib | http ]
[33] Florian Leitner et al. Introducing meta-services for biomedical information extraction. Genome Biology, 9(Suppl 2):S6, 2008. [ bib | http ]
[34] Beatrice Alex, Claire Grover, Barry Haddow, Mijail Kabadjov, Ewan Klein, Michael Matthews, Stuart Roebuck, Richard Tobin, and Xinglong Wang. Assisted curation: Does text mining really help? In Proceedings of Pacific Symposium on Biocomputing, Hawaii, USA, January 2008. [ bib | .pdf ]
[35] Barry Haddow and Michael Matthews. The extraction of enriched protein-protein interactions from biomedical text. In Biological, translational, and clinical language processing, pages 145-152, Prague, Czech Republic, June 2007. Association for Computational Linguistics. [ bib | .pdf ]
[36] Beatrice Alex, Barry Haddow, and Claire Grover. Recognising nested named entities in biomedical text. In Biological, translational, and clinical language processing, pages 65-72, Prague, Czech Republic, June 2007. Association for Computational Linguistics. [ bib | .pdf ]
[37] Claire Grover, Barry Haddow, Ewan Klein, Michael Matthews, Leif Nielsen, Richard Tobin, and Xinglong Wang. Adapting a Relation Extraction Pipeline for the BioCreAtIvE II Tasks. In Proceedings of the Second BioCreative Challenge Workshop, pages 273-286, Madrid, Spain, 2007. CNIO. [ bib | .pdf ]

What I Did Before

In 2005 I completed an MSc in Artificial Intelligence in Edinburgh University, specialising in Natural Language. Prior to that I worked for Orbism, a Dublin-based IT consultancy for several years. And going back even further, I gained a PhD in Mathematics from Aberdeen University, supervised by Graham Hall, in 1994.