dcsimg

Adrià de Gispert - Research Scientist

SDL Research - Cambridge, UK

SDL Research

SDL Research

Return to the people page

SDL Innovation

Discover SDL Research breakthroughs

SDL Research Careers

Explore opportunities at SDL

Research profile:

Adrià received his PhD on incorportating linguistic knowledge to ngram-based Statistical Machine Translation in January 2007. He spent the next 6 years as Research Associate, Lecturer in Speech and Language Technologies and Senior Research Associate at the University of Cambridge. He is a fellow of the Clare College, Cambridge. He has a strong research interest in many aspects of machine translation from word alignment all the way to re-scoring and system combination, and its connections with spoken and natural language processing, machine learning and parallel computing problems. He has substantial experience developing large-scale state-of-the-art SMT systems, particularly using finite-state automata.“ 

About Adrià

Education
Universitat Politècnica de Catalunya, PhD in Statistical Machine Translation, 2007 
Publications

2012
Gispert, A.,Blackwood, G., Iglesias G., & Byrne, W.  (2012) N-gram posterior probability confidence measures for statistical machine translation: an empirical study In Machine Translation, DOI: 10.1007/s10590-012-9132-2, 2012. [PDF]

Byrne, B., de Gispert, A., Iglesias, G., Pino, J., & Waite, R. (2012) The CUED OpenMT12 Arabic-English and Chinese-English SMT Systems. Presentation at NIST OpenMT Workshop, Washington (USA), June 2012. [PDF]

Parton, K., Habash, N., McKeown, K., Iglesias, G. & de Gispert, A. (2012)  Can Automatic Post-Editing Make MT More Meaningful? In Proc. of the Conf. of the European Association for Machine Translation (EAMT), Trento, Italy, May 2012. Best Paper Award. [PDF][bib]

2011
Iglesias, G., Allauzen, C., Byrne, W., de Gispert, A., & Riley, M. (2011)  Hierarchical Phrase-based Translation Representations. In Proc. of the Conf. on Empirical Methods in Natural Language Processing (EMNLP), Edinburgh, Scotland, July 2011. [PDF][slides][bib]

2010
de Gispert, A., Pino, J., & Byrne, W. (2010)  Hierarchical Phrase-based Translation Grammars Extracted from Alignment Posterior Probabilities. In Proc. of the Conf. on Empirical Methods in Natural Language Processing (EMNLP), Boston (MA), October 2010. [PDF][slides][bib]

de Gispert, A., Iglesias, G.,Blackwood, G., Banga, E.R., & Byrne, W. (2010) Hierarchical Phrase-based Translation with Weighted Finite State Transducers and Shallow-N Grammars. In Computational Linguistics, (36,3) 505-533. [PDF] [bib][errata]

Blackwood, G., de Gispert, A., & Byrne, W. (2010) Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices. In Proc. of the 23rd Int. Conf. on Computational Linguistics (COLING), Beijing, China, August 2010. [PDF] [bib]

Blackwood, G., de Gispert, A., & Byrne, W. (2010) Efficient Path Counting Transducers for Minimum Bayes-risk Decoding of Statistical Machine Translation Lattices. In Proc. of the 48th Annual Meeting of the Association for Computational Linguistics (ACL): Short papers, Uppsala, Sweden, July 2010. [PDF] [bib]

Pino, J., Iglesias, G.,de Gispert, A., Blackwood, G., Brunning, J., & Byrne, W. (2010) The CUED HiFST System for the WMT10 Translation Shared Task. In Proc. of the ACL Fifth Workshop on Statistical Machine Translation (WMT), Uppsala, Sweden, July 2010. [PDF] [bib]

2009
de Gispert, A., Iglesias, G., Blackwood, G., Brunning, J., & Byrne, W. (2009) The CUED NIST 2009 Arabic-English SMT System. Presentation at NIST MT Workshop, Ottawa (Canada), Aug 2009. [PDF]

Iglesias, G., de Gispert, A., Banga, E.R., & Byrne, W. (2009) Hierarchical Phrase-Based Translation with Weighted Finite State Transducers. In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), Boulder (CO), June 2009. [PDF] [bib]

Brunning, J., de Gispert, A., & Byrne, W. (2009) Context-dependent Alignment Models for Statistical Machine Translation. In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), Boulder (CO), June 2009. [PDF] [bib]

de Gispert, A., Virpioja, S., Kurimo, M., & Byrne, W.  (2009) Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions. In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT): Short papers., Boulder (CO), June 2009. [PDF] [bib]

Iglesias, G., de Gispert, A., Banga, E.R., & Byrne, W. (2009) The HiFst System for EuroParl Spanish-to-English task. In Proc. of the 25th Meeting of the Spanish Society for Natural Language Processing (SEPLN), Donosti, Spain, September 2009. [PDF] [bib]

Iglesias, G., de Gispert, A., Banga, E.R., & Byrne, W. (2009) Rule Filtering by Pattern for Efficient Hierarchical Translation. In Proc. of the 12th European Chapter of the Association for Computational Linguistics (EACL), Athens, Greece, April 2009. [PDF] [slides][bib]

2008
Blackwood, G., de Gispert, A., Brunning J., & Byrne, W. (2008) Large-scale statistical machine translation with weighted finite state transducers. In Frontiers in Artificial Intelligence and Applications, Vol. 191: Finite-State Methods and Natural Language Processing. Post-proceedings of the 7th Int. Workshop on Finite-State Methods and Natural Language Processing FSMNLP 2008. Piskorski, J.,  Watson, B., & Yli-Jyrä A. (Eds). IOS Press, 2009. [PDF] [slides]

de Gispert, A., & Mariño, J.B. (2008) On the impact of morphology in English to Spanish statistical MT. In Speech Communication, (50) 1034-1046. [PDF] [bib]

Blackwood, G., de Gispert, A., & Byrne, W.(2008) Phrasal Segmentation Models for Statistical Machine Translation. In Proc. of the 22nd Int. Conf. on Computational Linguistics (COLING), Manchester, UK, August 2008. [PDF] [bib]

Blackwood, G., de Gispert, A., Brunning J., & Byrne, W. (2008) European language translation with weighted finite state transducers: The CUED MT system for the 2008 ACL workshop on SMT. 
In Proc. of the ACL 2008 Third Workshop on Statistical Machine Translation, June 2008. [PDF] [bib]

 de Gispert, A., Blackwood, G., Brunning J., & Byrne, W. (2008) The CUED NIST 2008 Arabic-English SMT System. Presentation at NIST MT Workshop, Arlington (VA), Mar 2008.[PDF]

2007 (selection)
Liu, X.A.,  Byrne, W., Gales, M. J. F., de Gispert, A., Tomalin, M., Woodland, P. C., & Yu, K. (2007) Discriminative language model adaptation for Mandarin broadcast speech transcription and translationemptyIn Proc. IEEE Automatic Speech Recognition and Understanding (ASRU), Kyoto, Japan, Dec 2007. [PDF]

2006 (selection)
Mariño, J.B., Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa J.A.R., & Costa-jussà, M.R. (2006) N-gram-based Machine Translation.In Computational Linguistics. (32,4) 527-549. [PDF][bib]

de Gispert, A., & Mariño, J.B. (2006) Linguistic knowledge in statistical phrase-based word alignment. In Natural Language Engineering. (12,1) 91-108. Cambridge University Press. [PDF] [bib]

de Gispert, A., & Mariño, J.B. (2006b) Linguistic tuple segmentation in ngram-based statistical machine translation. In Proc. of the 9th Int. Conf. on Spoken Language Processing (Interspeech) , Pittsburgh (PA), Sep 2006. [PDF]

de Gispert, A., Gupta, D., Popovic, M., Lambert, P., Mariño, J.B., Federico, M., Ney H., & Banchs, R. (2006) Improving Statistical Word Alignments with Morpho-syntactic TransformationsIn Lecture Notes in Artificial Intelligence, (4139) Advances in Natural Language Processing. Proceedings of the 5th Int. Conference on Natural Language Processing FinTAL, pps 368-79. Salakoski, T., Ginter, F., Pyysalo, S., & Pahikkala, T. (Eds) Springer Berlin, August 2006. [PDF]

Popovic, M., de Gispert, A., Gupta, D., Lambert, P., Ney, H., Mariño, J.B., Federico, M. & Banchs, R. (2006) Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output. In HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT), New York City, June 2006. [PDF] [slides][bib]

Crego, J.M., de Gispert, A., Lambert, P., Costa-jussà, M.R., Khalilov, M., Banchs, R., Mariño,  J.B. & Fonollosa, J.A.R. (2006) N-gram-based SMT System Enhanced with Reordering Patterns.  In HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT), New York City, June 2006.[PDF] [slides][bib]

SDL Language Technologies

Complete technology solutions for translation and global communication

SDL BeGlobal

Machine Translations, translation more content at less cost.

Top 5 Big Language Business Problems

Solved by Machine Translation