Department of Engineering

Dr. Graeme Blackwood

I am now working for IBM Research in the Natural Language Processing group at the Watson Research Center in Yorktown Heights, New York. My new home page can be found here

Cambridge University

Graeme Blackwood was a postdoctoral Research Associate in the Machine Intelligence Laboratory of Cambridge University Engineering Department under the supervision of Dr. Bill Byrne.

In 2005 he graduated with an M.Phil. in Computer Speech, Text and Internet Technology from the Computer Laboratory of Cambridge University. In 2006 he continued as a Ph.D. research student studying statistical machine translation.

Graeme's Ph.D. thesis title is "Lattice Rescoring Methods for Statistical Machine Translation".

Research Interests

• Statistical Machine Translation
• Statistical Language Modelling

Research Projects

• AGILE - Autonomous Global Integrated Language Exploitation

Publications and Presentations

• Blackwood, G. (2011). Minimum Bayes-risk lattice rescoring methods for statistical machine translation. NLIP Seminar Series, Cambridge University Computer Laboratory. May 2011. Invited Talk. [slides]

• Blackwood, G. (2010). Lattice rescoring methods for statistical machine translation. Ph.D. Thesis. Cambridge University Engineering Department and Clare College. [pdf | summary]

• de Gispert, A., Iglesias, G., Blackwood, G., Banga, E. R., and Byrne, W. (2010). Hierarchical phrase-based translation with weighted finite state transducers and shallow-n grammars. In Computational Linguistics. Issue 36(3), September 2010. Association for Computational Linguistics. [pdf | bib]

• Blackwood, G., de Gispert, A., and Byrne, W. (2010). Fluency constraints for minimum Bayes-risk decoding of statistical machine translation lattices. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010). [pdf | bib | slides]

• Blackwood, G., de Gispert, A., and Byrne, W. (2010). Efficient path counting transducers for minimum Bayes-risk decoding of statistical machine translation lattices. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010). [pdf | bib | poster | slides | example]

• Pino, J., Iglesias, G., de Gispert, A., Blackwood, G., Brunning, J. and Byrne, W. (2010). The CUED HiFST system for the WMT10 translation shared task. In Proceedings of the ACL 2010 Joint Fifth Workshop on Statistical Machine Translation and Metrics MATR. [pdf | bib | poster]

• Kurimo, M., Virpioja, S., Turunen, V. T., Blackwood, G.W., and Byrne,W. (2009). Overview and results of morpho challenge 2009. In Multilingual Information Access Evaluation Vol. I-II, 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009, Corfu, Greece. Springer Lecture Notes in Computer Science. [pdf | bib]

• de Gispert, A., Iglesias, G., Blackwood, G., Brunning, J., and Byrne, W. (2009). The CUED NIST 2009 Arabic-English SMT System. NIST Open Machine Translation 2009 Evaluation (MT09) Workshop, August 2009. [slides]

• Blackwood, G., de Gispert, A., and Byrne, W. (2008). Phrasal segmentation models for statistical machine translation. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING), Manchester, UK, August 2008. [pdf | bib | poster]

• Blackwood, G., de Gispert, A., Brunning, J., and Byrne, W. (2008). Large-scale statistical machine translation with weighted finite state transducers. In FSMNLP 2008 - Finite-State Methods and Natural Language Processing, Ispra, Lago Maggiore, Italy, September 2008. [pdf | bib]

• Blackwood, G., de Gispert, A., Brunning, J., and Byrne, W. (2008). European language translation with weighted finite state transducers: The CUED MT system for the 2008 ACL workshop on SMT. In Proceedings of the Third Workshop on Statistical Machine Translation, pages 131-134, Columbus, Ohio, June. Association for Computational Linguistics. [pdf | bib]

• de Gispert, A., Blackwood, G., Brunning, J., and Byrne, W. (2008). The CUED NIST 2008 Arabic-English SMT System. Presented at NIST MT Workshop, March 2008. [slides]

• Blackwood, G. (2005). Neural network-based language model for conversational telephone speech recognition. M.Phil. Thesis. Machine Intelligence Laboratory, Department of Engineering, University of Cambridge. [pdf | slides]