Home ] [ Adria de gispert ] [ Research ] [ Publications ] [ Links ]

   

 

 


Adrià de Gispert

TALP Research Center (UPC)

UPC Campus Nord (D5-214)
c/ Jordi Girona 1-3
08034 Barcelona (Catalunya)
Tel: +34 93 401 0964

FAX: +34 93 401 0447

e-mail: agispert@gps.tsc.upc.edu

IMPORTANT NOTE: This website is obsolete. My current website is here.

I am a PhD student (under FI grant) at Universitat Politècnica de Catalunya (UPC), Barcelona, since Sep 2001. I received my Telecommunications Engineer degree at UPC in that year. My PhD research topic is Statistical Machine Translation, particularly when merging existent linguistic knowledge into statistical processes.


Research Interests

Statistical Machine Translation (SMT):

  • Ngram-based Statistical Machine Translation.
  • Statistical word alignment.
  • Introducing linguistic knowledge into SMT.
  • Phrase-based Statistical Machine Translation.
  • Speech to Speech Translation.

Other interests

  • Natural Language Processing tasks (tagging, parsing, chunking,...)
  • Linguistics.
  • Speech recognition.

Demos & Software

  • N-II : A statistical machine translator between Spanish and Catalan
  • MARIE : An Ngram-based Statistical Machine Translation Decoder

    Projects

  • TC-STAR: Technology and Corpora for Speech to Speech Translation
  • ALIADO: Tecnologías del Habla y el Lenguaje para un Asistente Personal

    Publications

    Statistical Machine Translation

    2006
  • Mariño, J.B., Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa, J.A.R. and Costa-jussà, M.R. N-gram-based Machine Translation.
    Computational Linguistics, Volume 32, Number 4, pp. 527-549, Dec 2006.
  • Crego, J.M., de Gispert, A., Lambert, P., Khalilov, M., Costa-jussà, M.R., Mariño, J.B., Banchs, R. and Fonollosa, J.A.R.The TALP Ngram-based SMT System for IWSLT 2006
    Proc. of the 3rd Int. Workshop on Spoken Language Translation (IWSLT'06), pp. 116-122. Tokyo (Japan), Dec 2006.
  • Costa-jussà, M.R., Crego, J.M., de Gispert, A., Lambert, P., Khalilov, M., Fonollosa, J.A.R., Mariño, J.B. and Banchs, R.TALP Phrase-Based System and TALP System Combination for IWSLT 2006
    Proc. of the 3rd Int. Workshop on Spoken Language Translation (IWSLT'06), pp. 123-129. Tokyo (Japan), Dec 2006.
  • de Gispert, A. and Mariño, J.B. Linguistic tuple segmentation in ngram-based statistical machine translation
    Proc. of the 9th Int. Conf. on Spoken Language Processing (Interspeech'06), pp. 1149-52. Pittsburgh (PA), Sep 2006.
  • de Gispert, A. and Mariño, J.B. Segmentación lingüística de tuplas para el modelado de la traducción estocástica mediante n-gramas
    Procesamiento del Lenguaje Natural, núm. 37 (SEPLN'06), pp. 241-48. Zaragoza (Spain), Sep 2006.
  • de Gispert, A. Gupta, D., Popovic, M., Lambert, P., Mariño, J.B., Federico, M., Ney, H. and Banchs, R. Improving Statistical Word Alignments with Morpho-syntactic Transformations
    Proc. of 5th Int. Conf. on Natural Language Processing (FinTAL'06), pp. 368-379. Turku (Finland), August 2006.
  • Popovic, M., de Gispert, A. Gupta, D., Lambert, P., Ney, H., Mariño, J.B., Federico, M. and Banchs, R. Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output [slides]
    HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT'06), pp. 1-6. New York City, June 2006.
  • Costa-jussà, M.R., Crego, J.M., de Gispert, A., Lambert, P., Khalilov, M., Mariño, J.B., Fonollosa, J.A.R., and Banchs, R. TALP Phrase-based statistical translation system for European language pairs
    HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT'06), pp. 142-145. New York City, June 2006.
  • Crego, J.M., de Gispert, A., Lambert, P., Costa-jussà, M.R., Khalilov, M., Banchs, R., Mariño, J.B. and Fonollosa, J.A.R. N-gram-based SMT System Enhanced with Reordering Patterns [slides]
    HLT/NAACL 2006 Workshop on Statistical Machine Translation (WMT'06), pp. 162-165. New York City, June 2006.
  • Mariño, J.B., Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa, J.A.R., Costa-juss\`a, M.R. and Khalilov, M. UPC's Bilingual N-gram Translation System
    TC-STAR Workshop on Speech-to-Speech Translation (TCSTAR'06), pp. 43-48. Barcelona, June 2006.
  • de Gispert, A. and Mariño, J.B. Catalan-English Statistical Machine Translation without Parallel Corpus: Bridging through Spanish
    Proc. of LREC 5th Workshop on Strategies for developing Machine Translation for Minority Languages (SALTMIL'06), pp. 65-68. Genova (Italy), May 2006.
  • de Gispert, A. and Mariño, J.B. Linguistic knowledge in statistical phrase-based word alignment.
    Natural Language Engineering, Volume 12, Issue 01, March 2006. pp 91-108. Cambridge University Press.
    2005
  • Lambert, P. de Gispert, A., Banchs, R. and Mariño, J.B. Guidelines for Word Alignment Evaluation and Manual Alignment
    Language Resources and Evaluation, Volume 39, Number 4, December 2005. pp 267-285. Springer Netherlands.
  • Crego, J.M., de Gispert, A. and Mariño, J.B. The TALP Ngram-based SMT System for IWSLT'05 [slides]
    Proc. of the 2nd Int. Workshop on Spoken Language Translation (IWSLT'05), pp. 191-198. Pittsburgh (PA), Oct 2005.
  • Mariño, J.B., Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa, J.A.R. and Ruiz, M. Bilingual N-gram Statistical Machine Translation
    Proc. of the 10th Machine Translation Summit (MTsummit'05), pp. 275-82. Pukhet (Thailand), Sep 2005.
  • Crego, J.M., Mariño, J.B. and de Gispert, A. Reordered Search and Tuple Unfolding for Ngram-based SMT
    Proc. of the 10th Machine Translation Summit (MTsummit'05), pp. 283-89. Pukhet (Thailand), Sep 2005.
  • de Gispert, A., Mariño, J.B. and Crego, J.M. Improving Statistical Machine Translation by Classifying and Generalizing Inflected Verb Forms [slides]
    Proc. of the 9th European Conf. on Speech Communication and Technology (Interspeech'05), pp. 3185-88. Lisboa (Portugal), Sep 2005.
  • Crego, J.M., Mariño, J.B. and de Gispert, A. An Ngram-based Statistical Machine Translation Decoder
    Proc. of the 9th European Conf. on Speech Communication and Technology (Interspeech'05), pp. 3193-96. Lisboa (Portugal), Sep 2005.
  • Mariño, J.B., Banchs, R., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa, J.A.R. and Costa-jussà, M.R. Modelo estocástico de traducción basado en N-gramas de tuplas bilingües y combinación log-lineal de características
    Procesamiento del Lenguaje Natural, núm. 35 (SEPLN'05), pp. 69-76. Granada (Spain), Sep 2005.
  • de Gispert, A., Mariño, J.B. and Crego, J.M.Clasificación y generalización de formas verbales en sistemas de traducción estocástica
    Procesamiento del Lenguaje Natural, núm. 35 (SEPLN'05), pp. 335-42. Granada (Spain), Sep 2005.
  • Crego, J.M., Mariño, J.B. and de Gispert, A. Algoritmo de Decodificación de Traducción Automática Estocástica basado en N-gramas [slides]
    Procesamiento del Lenguaje Natural, núm. 35 (SEPLN'05), pp. 85-92. Granada (Spain), Sep 2005.
  • de Gispert, A. Phrase Linguistic Classification and Generalization for Improving Statistical Machine Translation
    Proc. of the ACL Student Research Workshop (ACL'05/SRW), pp. 67-72. Ann Arbor (Michigan), June 2005.
  • Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P. and Mariño, J.B. Statistical Machine Translation of Euparl Data by using Bilingual N-grams [slides]
    Proc. of the ACL Workshop on Building and Using Parallel Texts (ACL'05/Wkshp), pp. 133-136. Ann Arbor (Michigan), June 2005.
    2004
  • de Gispert, A., Mariño, J.B. and Crego, J.M. TALP: Xgram-based Spoken Language Translation System [slides]
    Proc. of the Int. Workshop on Spoken Language Translation (IWSLT'04), pp. 85-90. Kyoto (Japan), Oct 2004.
  • de Gispert, A., Mariño, J.B. and Crego, J.M. Phrase-based alignment combining corpus cooccurrences and linguistic knowledge [slides]
    Proc. of the Int. Workshop on Spoken Language Translation (IWSLT'04), pp. 107-114. Kyoto (Japan), Oct 2004.
  • Crego, J.M., Mariño, J.B. and de Gispert, A. Finite-state-based and Phrase-based Statistical Machine Translation
    Proc. of the 8th Int. Conf. on Spoken Language Processing (ICSLP'04), Jeju (S.Korea), Oct 2004.
    2003 and previous
  • de Gispert, A. and Mariño, J.B. Experiments in word-ordering and morphological preprocessing for transducer-based statistical machine translation
    Proc. of 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'03), pp. 634-639. St.Thomas (USA), Dec 2003.
  • de Gispert, A. and Mariño, J.B. Using X-grams for Speech-to-Speech Translation
    Proc. of the 7th Int. Conf. on Spoken Language Processing (ICSLP'02), pp. 1885-1888. Denver, CO (USA), Sep 2002.
  • de Gispert, A. and Mariño, J.B. Análisis de las relaciones cruzadas en el alineado estadístico para la traducción automática
    II Jornadas en Tecnología del Habla, Granada (Spain), Dec 2002.

    Others

  • Arranz, V., Castell, N., Crego, J.M., Gimenez, J., de Gispert, A. and Lambert, P. Bilingual connections for Trilingual Corpora: An XML approach.
    4th Int. Conf. on Language Resources and Evaluation (LREC'04), Lisbon (Portugal), May 2004.
  • Màrquez, Ll., de Gispert, A., Carreras, X. and Padró, Ll. Low-cost Named Entity Classification for Catalan: Exploiting Multilingual Resources and Unlabeled Data.
    Proc. of the ACL Workshop on Multilingual and Mixed-language Named Entity Recognition: Combining Statistical and Symbolic Models (MulNER'03), Sapporo (Japan), July 2003.

  • Send us any suggestion ag_mail.gif (994 bytes)

    This page was last updated on December 05th, 2006