Associate Professor
                                     Ph.D. in Computer Science
Departament de Llenguatges i Sistemes Informàtics
                          Universitat Politècnica de Catalunya
LM picture   Tel:  +34-93-4137866
  Fax: +34-93-4137833
  E-mail: lluism at one of the following lsi.upc.edu/talp.upc.edu           
  Address: Despatx S120 - Edifici Omega - Campus Nord UPC
  Carrer Jordi Girona Salgado 1-3
  08034, Barcelona, Catalonia, Spain


I am a member of the Natural Language Processing Research Group (GPLN) at the Software Department. GPLN is a member of TALP Research Center (on Techniques and Applications of Language and Speech). My research in the last ten years has been devoted to the application of Machine Learning techniques to Natural Language Processing problems. My PhD thesis (from July 1999) was about the application of decision tree induction to the problem of Part-of-speech tagging.
My current interests are focused on:

       Machine learning algorithms and architectures (esp. for structured and relational classification)
       Joint resolution of multiple-level NLP tasks
       Specific NLP problems: POS tagging, word sense disambiguation, named entity extraction, shallow and full parsing, semantic role labeling.
       Specific NLP applications: Statistical Machine Translation using linguistic knowledge, Oral Question Answering

Keywords: Artificial Intelligence, Natural Language Processing, Computational Linguistics, Machine Learning, Natural Language Learning

Curriculum Vitae
(updated May 2012; upon request)

   Articles in international refereed conferences and journals, book chapters, etc.
Tutorial on Semantic Role Labeling at ACL-IJCNLP 2009 (pdf, bibliography)

Current research projects
FAUST project: Feedback Analysis for User Adaptive Statistical Translation (FP7-ICT-2009-4-247762, EC, 2010-2012)
   MOLTO project: Multilingual On-Line Translation (FP7-ICT-2009-4-247914, EC, 2010-2012)
   OpenMT-2: Traducción automática híbrida y evaluación avanzada (TIN2009-14675-C03, Spanish MICINN project, 2010-2012)
   QUESTIA: Motor de respuestas escalable capaz de responder a las preguntas expresadas directamente en lenguaje natural (TSI-020100-2010-210, Spanish Avanza project, 2010-2011). The technology developed in this project will be used in the fogg travel search engine

Recent and past activities and service (2012-2004)
   Program co-chair of EACL-2012, with Mirella Lapata
   Guest Editor of the Special Issue on Statistical Learning of Natural Language Structured Input and Output at Natural Language Engineering journal (2010-2011) together with Alessandro Moschitti
   Co-organizer of the ACL HLT 2011 TextGraphs-6 Workshop (Graph-based Methods for Natural Language Processing), together with Irina Matveeva, Alessandro Moschitti and Fabio Massimo Zanzotto
   Local organizer of LIHMT-2011, the OpenMT-2 International Workshop on Using Linguistic Information for Hybrid Machine Translation; Barcelona, October 2011
   Secretary/President of SIGNLL (2007-2011), the ACL Special Interest Group on Natural Language Learning
   Program co-chair of EMNLP 2010, with Hang Li
Tutorial co-chair of ACL 2010, with Haifeng Wang
   Co-organizer of the SemEval-2010 task: Coreference Resolution in Multiple Languages, with M.A. Martí, M. Recasens, E. Sapena and M. Taulé.
   Co-organizer (with Eneko Agirre and Richard Wicentowski) of the SEW-2009 Workshop at NAACL-HLT 2009, Boulder, Colorado, June 4, 2009.
   Co-organizer and program Co-chair (with Harold Somers) of the 13th Annual Conference of the European Association for Machine Translation (EAMT-2009), Barcelona, May 14-15, 2009.
   Co-organizer of the CoNLL-2009 shared task Syntactic and Semantic Dependencies in Multiple Languages, Boulder, Colorado, June 4-5, 2009 
   Guest Editor of the Special Issue on Computational Semantic Analysis of Language: SemEval-2007 and Beyond at Language Resources and Evaluation, together with Eneko Agirre and Richard Wicentowski, 2009     
   Co-organizer of the CoNLL-2008 shared task Joint Parsing of Syntactic and Semantic Dependencies, Manchester, UK, August 16-17, 2008
   Guest Editor of the Special Issue on Semantic Role Labeling at Computational Linguistics, 34(2), together with Xavier Carreras, Ken Litkowski, and Suzanne Stevenson, 2008
   I co-chaired the MATMT2008 workshop "Mixing Approaches to Machine Translation", Donostia-San Sebastian, February 14, 2008   
   I co-chaired with Richard Wicentowski and Eneko Agirre the SemEval-2007 evaluation exercise and workshop on semantic analysis, 2007
   I co-organized with M. Antònia Martí, Mariona Taulé (CLiC, UB) and Luis Villarejo the SemEval-2007 task on Multilevel Semantic Annotation of Catalan and Spanish, 2007
   I co-chaired with Dan Klein the tenth Conference on Computational Language Learning (a.k.a CoNLL-X), June 2006
   I co-chaired with Xavier Carreras the CoNLL-2005 Shared Task competition on Semantic Role Labelling, July 2005
   I co-chaired with Xavier Carreras the CoNLL-2004 Shared Task Competition on Semantic Role Labelling, May 2004
   I coordinated the organization of the Senseval-3 "lexical sample" tasks on Catalan and Spanish WSD, July 2004
   Mini-symposium on Structural Inference & Learning with Constraints at CCG, UIUC, June 2004

Current Ph.D. students

    Xavier Lluís (LSI, UPC)
    Eva Martínez (LSI, UPC)

PostDoc visitors
    Daniele Pighin (UPC postdoc grant + FAUST project: 2010-2012)
    Alberto Barrón (ERCIM fellow: 2012-2013)

Former Ph.D. students
    Pere R. Comas (LSI, UPC): graduated in June 2012; Co-advised with Jordi Turmo (LSI, UPC)
    Beñat Zapirain (UPV/EHU): graduated in Juanuary 2011; Co-advisor Eneko Agirre (UPV/EHU)
    Jesús Giménez (LSI, UPC): graduated in July 2008 (now at Google, Dublin)
    Gerard Escudero (LSI, UPC): graduated in July 2006; Co-advisor German Rigau (UPV/EHU)
    Xavier Carreras (LSI, UPC): graduated in October 2005;
    Antoni Oliver (Universitat de Barcelona): graduated in July 2004; Currently at UPF; Co-advisor Irene Castellón (UB)
    Jordi Duran (LSI, UPC); DEA in June 2008
    Luis Villarejo (LSI, UPC); DEA in June 2008
    Miguel Ángel García (LSI, UPC); DEA in June 2008

Master Theses (Artificial Inteligence program: 2006-2008)
    Xavier Lluís (LSI, UPC): July 2008
    Cristina España (LSI, UPC): February 2008


Under-graduate courses
    2011/12 (Spring semester) Teoria de la Computació (web de TC a la FIB; Enginyeries pla 2003)
    2009/10 Programació I (web de P1 a la FIB)
    2008/09 Fonaments d'Informàtica (web de LSI a l'EPSEM)
    2007/08 (Fall semester) Teoria de la Computació (web de TC a la FIB)
    2006/07 (Spring Semester) Introducció a la Lògica (web de IL a la FIB)

Courses at the AI master
    Course 2011/12 (Fall semester) Natural Language Processing for Massive Textual Data Management (PLN-PMT)

Post-graduate courses at the AI PhD Program (now subsumed by master studies)
    Course 2005/06, 1st semester: Empirical Methods for Natural Language Processing (EMNLP)
    Course 2003/04, 2nd semester: Advanced Topics in  Natural Language Processing (ATNLP
    Course 1999/00: Tècniques de Tractament del Llenguatge Natural (TTLN): Aprenentatge Automàtic i Llenguatge Natural

 MELP Summer School
    Course 2002/03 (Barcelona, July 2003):
Machine Learning for Natural Language Processing

Last updated: June 27, 2012