Dr. Gonzalo Iglesias

I am a Research Associate under the FAUST project: Feedback Analysis for User adaptive Statistical Translation (FP7-ICT-2009-4). I work in Statistical Machine Translation (SMT) at the Division of Information Engineering, computer, control & mathematics, in the Machine Intelligence Laboratory. Check the Cambridge Engineering Department SMT team wiki page for ongoing news.
I received my PhD in Statistical Machine Translation (SMT) from the Department of Signal Theory and Communications of the Universidade de Vigo on March 2010, which describes several strategies to reduce the search space described by hierarchical grammars with a minimum impact on performance, and a new type of hierarchical decoder based on lattices implemented with WFSTs, capable of avoiding pruning-in-search for many translation tasks.

Publications and Presentations

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

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

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

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

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

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

• Hierarchical Phrase-based Translation with Weighted Finite State Transducers. G. Iglesias
  PhD, University of Vigo, March 2010. Advisors: A. de Gispert and E. R. Banga. EAMT 2010 Best Thesis Award. [pdf][bib]

• The HiFst System for EuroParl Spanish-to-English task. G. Iglesias, A. de Gispert, E. R. Banga, and W. Byrne.
  In XXV edición del Congreso Anual de la Sociedad Española para el Procesamiento del Lenguaje Natural
  Donostia-San Sebastián, Spain, September 2009. [pdf][bib][slides]

• Hierarchical Phrase-Based Translation with Weighted Finite State Transducers. G. Iglesias, A. de Gispert, E. R. Banga, and W. Byrne.
  Proc. of North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) 2009 conference.
  Boulder (Colorado, USA), June 2009. [pdf][bib][slides]
• Rule Filtering by Pattern for Efficient Hierarchical Translation. G. Iglesias, A. de Gispert, E. R. Banga, and W. Byrne.
  Proc. of the 12th European Chapter of the Association for Computational Linguistics conference (EACL) 2009 conference.
  Athens, Greece, April 2009. [pdf][bib][slides]
• Specific features of the Galician language and implementations for speech technology.. Manuel González González, Eduardo Rodríguez Banga, Francisco Campillo Díaz, Francisco Méndez Pazó, Leandro Rodríguez Liñares, Gonzalo Iglesias Iglesias.
  Speech Communication vol 50, pp 874-887. November 2008.
• Descripción del sintetizador de voz COTOVÍA para la evaluación ALBAYZIN TTS 2008. Eduardo R. Banga, Francisco Méndez, Francisco Campillo, Gonzalo Iglesias, Laura Docío.
  Las Tecnologías del Habla, ISBN 978-84-9860-169-5.
  Bilbao,Spain, November 2008
• Perspectivas de la traducción automática castellano-gallego mediante técnicas estadísticas y por transferencia. Gonzalo Iglesias Iglesias, Leandro Rodríguez Liñares, Eduardo Rodríguez Banga, Francisco Campillo Díaz, Francisco Méndez Pazó.
  Las Tecnologías del Habla, ISBN 84-06214-82-6.
  Zaragoza Spain, September 2006.
• Desarrollo de un sistema de análisis sintáctico para el idioma gallego. Francisco Campillo Díaz, Leandro Rodríguez Liñares, Eduardo Rodríguez Banga, Gonzalo Iglesias Iglesias, Francisco Méndez Pazó. Las Tecnologías del Habla, ISBN 84-95118-58-0. Valencia,Spain, September 2004.

E-mail:	gi212 AT eng.cam.ac.uk
Post:	University of Cambridge, Department of Engineering, Trumpington Street, Cambridge CB2 1PZ
Telephone:	+44 1223 7 46998
Fax:	+44 1223 3 32662