Department of Engineering

Dr Adrià de Gispert Senior Research Associate Statistical Machine Translation

I work in Statistical Machine Translation (SMT), and my interests include statistical modeling of speech and text, natural language processing and computational linguistics.
My recent work is focused on developing translation systems that apply models of induced syntax for multiple language pairs.
The University of Cambridge Engineering Department SMT team has a wiki here: http://divf.eng.cam.ac.uk/smt

I am a member of the Speech Research Group, in the Machine Intelligence Laboratory in the Information Engineering Division. I also hold a College Assistant Lecturer position at Clare College, where I teach Engineering supervisions.

• Projects I am working (or have worked) on
  • FAUST: Feedback Analysis for User adaptive Statistical Translation (FP7-ICT-2009-4)
  • International Evaluations in Machine Translation: NIST Open MT Evaluations, DARPA GALE MT Evaluations, WMT shared tasks
  • AGILE: Autonomous Global Integrated Language Exploitation
  • Past Research Projects (at UPC, Barcelona): TC-STAR (EC FP6-506738), FAME (EC IST-2000-28323), ALIADO (Spanish Gvmt TIC2002-04447-C02)
• Teaching (past)
  • 2010-11: Masters in Advanced Computer Science
    • Spoken Language Processing (syllabus) -- local pages
    • Statistical Machine Translation (syllabus) -- local pages
  • 2010-11: Fourth Year Engineering Undergraduates
    • Module 4F11 - Speech and Language Processing -- local pages
  • 2009-10: Masters in Computer Speech, Text and Internet Technology
    • Module 1A: Speech Signal Processing, Speech Recognition
  • 2009-10: Fourth Year Engineering Undergraduates
    • Module 4F11 - Speech and Language Processing -- local pages

Background

I received my PhD in Statistical Machine Translation (SMT) from the Dept. of Signal Theory and Communications of the Universitat Politècnica de Catalunya (UPC) in Barcelona, in January 2007. My dissertation studied Ngram-based SMT models and how to incorporate linguistic information into the statistical translation framework (download).
From January 2007 to August 2009 I worked as a post-doc Research Associate at the Engineering Department of the University of Cambridge.
From September 2009 to August 2011 I was a fixed-term Lecturer in Speech and Language Technologies at the Engineering Department of the University of Cambridge.

Publications

2010-2011

• G. Iglesias, C. Allauzen, W. Byrne, A. de Gispert and M. Riley. (2011)
  Hierarchical Phrase-based Translation Representations [slides] [bib]
  In Proc. of the Conf. on Empirical Methods in Natural Language Processing (EMNLP), Edinburgh, Scotland, July 2011.
• A. de Gispert, J. Pino and W. Byrne. (2010)
  Hierarchical Phrase-based Translation Grammars Extracted from Alignment Posterior Probabilities [slides] [bib]
  In Proc. of the Conf. on Empirical Methods in Natural Language Processing (EMNLP), Boston (MA), October 2010.
• A. de Gispert, G. Iglesias, G. Blackwood, E.R. Banga and W. Byrne. (2010)
  Hierarchical Phrase-based Translation with Weighted Finite State Transducers and Shallow-N Grammars [bib] [ errata ]
  In Computational Linguistics, Volume 36, Number 3, pp. 505-533, 2010.
• G. Blackwood, A. de Gispert and W. Byrne. (2010)
  Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices [bib]
  In Proc. of the 23rd Int. Conf. on Computational Linguistics (COLING), Beijing, China, August 2010.
• G. Blackwood, A. de Gispert and W. Byrne. (2010)
  Efficient Path Counting Transducers for Minimum Bayes-risk Decoding of Statistical Machine Translation Lattices [bib]
  In Proc. of the 48th Annual Meeting of the Association for Computational Linguistics (ACL): Short papers, Uppsala, Sweden, July 2010.
• J. Pino, G. Iglesias, A. de Gispert, G. Blackwood, J. Brunning and W. Byrne. (2010)
  The CUED HiFST System for the WMT10 Translation Shared Task [bib]
  In Proc. of the ACL Fifth Workshop on Statistical Machine Translation (WMT), Uppsala, Sweden, July 2010.

2008-2009

• A. de Gispert, G. Iglesias, G. Blackwood, J. Brunning and W. Byrne. (2009)
  The CUED NIST 2009 Arabic-English SMT System.
  Presentation at NIST MT Workshop, Ottawa (Canada), Aug 2009.
• G. Iglesias, A. de Gispert, E. R. Banga and W. Byrne. (2009)
  Hierarchical Phrase-Based Translation with Weighted Finite State Transducers. [bib]
  In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), Boulder (CO), June 2009.
• J. Brunning, A. de Gispert and W. Byrne. (2009)
  Context-dependent Alignment Models for Statistical Machine Translation. [bib]
  In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), Boulder (CO), June 2009.
• A. de Gispert, S. Virpioja, M. Kurimo and W. Byrne. (2009)
  Minimum Bayes Risk Combination of Translation Hypotheses from Alternative Morphological Decompositions. [bib]
  In Proc. of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT): Short papers., Boulder (CO), June 2009.
• G. Iglesias, A. de Gispert, E. R. Banga and W. Byrne. (2009)
  The HiFst System for EuroParl Spanish-to-English task. [bib]
  In Proc. of the 25th Meeting of the Spanish Society for Natural Language Processing (SEPLN), Donosti, Spain, September 2009.
• G. Iglesias, A. de Gispert, E. R. Banga and W. Byrne. (2009)
  Rule Filtering by Pattern for Efficient Hierarchical Translation. [slides] [bib]
  In Proc. of the 12th European Chapter of the Association for Computational Linguistics (EACL), Athens, Greece, April 2009.
• G. Blackwood, A. de Gispert, J. Brunning and W. Byrne. (2008)
  Large-scale statistical machine translation with weighted finite state transducers. [slides]
  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. Edited by J. Piskorski, B. Watson and A. Yli-Jyrä. IOS Press, 2009.
• A. de Gispert and J.B. Mariño. (2008)
  On the impact of morphology in English to Spanish statistical MT. [bib]
  In Speech Communication, Volume 50, pp. 1034-1046, 2008.
• G. Blackwood, A. de Gispert and W. Byrne. (2008)
  Phrasal Segmentation Models for Statistical Machine Translation. [bib]
  In Proc. of the 22nd Int. Conf. on Computational Linguistics (COLING), Manchester, UK, August 2008.
• G. Blackwood, A. de Gispert, J. Brunning and W. Byrne. (2008)
  European language translation with weighted finite state transducers: The CUED MT system for the 2008 ACL workshop on SMT. [bib]
  In Proc. of the ACL 2008 Third Workshop on Statistical Machine Translation, June 2008.
• A. de Gispert, G. Blackwood, J. Brunning and W. Byrne. (2008)
  The CUED NIST 2008 Arabic-English SMT System.
  Presentation at NIST MT Workshop, Arlington (VA), Mar 2008.

2006-2007 (selection)

• X. A. Liu, W. J. Byrne, M. J. F. Gales, A. de Gispert, M. Tomalin, P. C. Woodland and K. Yu. (2007)
  Discriminative language model adaptation for Mandarin broadcast speech transcription and translation.
  In Proc. IEEE Automatic Speech Recognition and Understanding (ASRU), Kyoto, Japan, Dec 2007.
• J.B. Mariño, R.E. Banchs, J.M. Crego, A. de Gispert, P. Lambert, J.A.R. Fonollosa and M.R. Costa-jussà. (2006)
  N-gram-based Machine Translation. [bib]
  In Computational Linguistics, Volume 32, Number 4, pp. 527-549, 2006.
• A. de Gispert and J.B. Mariño. (2006)
  Linguistic knowledge in statistical phrase-based word alignment. [bib]
  In Natural Language Engineering, Volume 12, Issue 01, March 2006. pp 91-108. Cambridge University Press.
• A. de Gispert and J.B. Mariño. (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.
• A. de Gispert, D. Gupta, M. Popovic, P. Lambert, J.B. Mariño, M. Federico, H. Ney and R. Banchs. (2006)
  Improving Statistical Word Alignments with Morpho-syntactic Transformations.
  In Lecture Notes in Artificial Intelligence, Vol. 4139: Advances in Natural Language Processing. Proceedings of the 5th Int. Conference on Natural Language Processing FinTAL, pps 368-79. Edited by T. Salakoski, F. Ginter, S. Pyysalo and T. Pahikkala. Springer Berlin, August 2006.
• M. Popovic, A. de Gispert, D. Gupta, P. Lambert, H. Ney, J.B. Mariño, M. Federico and R. Banchs. (2006)
  Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output [slides] [bib]
  In HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT), New York City, June 2006.
• J.M. Crego, A. de Gispert, P. Lambert, M.R. Costa-jussà, M. Khalilov, R. Banchs, J.B. Mariño and J.A.R. Fonollosa (2006)
  N-gram-based SMT System Enhanced with Reordering Patterns [slides] [bib]
  In HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT), New York City, June 2006.

2002-2006

Complete list of publications until December 2006 can be accessed HERE (previous website from UPC).

Other talks and activities

• A. de Gispert (2011)
  Hierarchical Phrase-Based Translation at University of Cambridge
  Talk at Barcelona Media Innovation Centre, Barcelona, Catalonia (Spain), July 2011.
  Talk at Catalonia Research Group on Accessibility and Ambient Intelligence (CaiaC), Universitat Autònoma de Catalunya, Bellaterra, Catalonia (Spain), July 2011.
• G. Iglesias, C. Allauzen, W. Byrne, A. de Gispert and M. Riley (2011)
  Hierarchical Phrase-Based Representations: Decoding with Push-Down Transducers and Entropy-Pruned Language Models
  Talk at GALE PI Meeting, Arlington, VA (USA), May 2011.
• A. de Gispert (2011)
  Hierarchical Phrase-Based Translation at University of Cambridge
  Talk at Google Research Labs, Mountain View, CA (USA), May 2011.
• A. de Gispert (2010)
  Hierarchical phrase-based translation with weighted finite state transducers.
  Talk at IST / INESC-id, Lisbon (Portugal), July 2010.
• A. de Gispert (2009)
  Statistical Machine Translation.
  10-hour tutorial presented for PhD programme at Universidad de Vigo, Spain, May 2009. Please contact for slides.
• A. de Gispert, X. A. Liu, W. J. Byrne, M. J. F. Gales and P. C. Woodland (2008)
  Broadcast Speech Transcription and Translation.
  Poster at Horizon Seminar: The Thinking Machine?, Emmanuel College, Cambridge (UK), Mar 2008.
• A. de Gispert (2007,2008)
  La Traducción Automática Estadística (TAE). ¿Pueden las máquinas traducir?.
  Talk at Cambridge University Engineering Department Language Unit, Cambridge (UK), Nov 2007 and Oct 2008.
• A. de Gispert (2006)
  Introducing morpho-syntax information into Ngram-based Statistical Machine Translation
  Talk at Seminari de Lingüística Computacional, Universitat Pompeu Fabra, Barcelona (Spain), Dec 2006.
• A. de Gispert (2006)
  Use of linguistic information and reordering stratregies for Ngram-based SMT
  Talk at Machine Intelligence Laboratory Speech Seminar, University of Cambridge (UK), Oct 2006.

Contact Information

University of Cambridge	Tel: +44 (0)1223 7 46998
Department of Engineering	email: ad465 at cam dot ac dot uk
Trumpington Street
Cambridge CB2 1PZ
United Kingdom

| Search | CUED | Cambridge University |

© 2005 Cambridge University Engineering Dept Information provided by milab-maintainer