Experts & Expertise

• Aanbevelingssysteem
• Computerlinguistiek
• Kunstmatige intelligentie
• Spraaktechnologie
• Sprekende computer
• Syntaxis
• Taaltechnologie

• Ph.D. (December 11, 1997). Thesis: Learning to pronounce written words: A study in inductive language learning. Universiteit Maastricht. Promotor: prof. dr. H.J. van den Herik; co-promotors: dr. A.J.M.M. Weijters, prof. dr. E.O. Postma. cum laude.
• MA (May 20, 1992). Tilburg University.

• Full professor, Dept. of Communication and Information Sciences and Tilburg centre for Creative Computing, Faculty of Humanities, Tilburg University. Jan 2008 - present.
• Associate professor, Dept. of Communication and Information Sciences, Faculty of Humanities, Tilburg University. Feb 2006 - Dec 2007.
  
• Guest professor, Centre for Dutch Language and Speech, Faculty of Arts, University of Antwerp, Antwerp, Belgium. Jan 2005 - present.
• Visiting faculty, WhizBang! Labs - Research, Pittsburgh, PA, USA. Sep - Dec 2001.
  
• Assistant professor, Computational Linguistics and Artificial Intelligence research unit, Faculty of Arts, Tilburg University. Feb 2001 - Feb 2006.
• Academy researcher, Fellow of the Koninklijke Nederlandse Academie van Wetenschappen (KNAW, Royal Dutch Academy of Arts and Sciences), Faculty of Arts, Computational Linguistics and Artificial Intelligence research unit, Tilburg University, the Netherlands. Jun 1999 - Feb 2001.

Ik doe onderzoek naar computationele implementaties van op analogie gebaseerde systemen voor de verwerking van natuurlijke taal. Deze systemen, die hun oorsprong hebben in de patroonherkenning en kunstmatige intelligentie, bieden het type analoog redeneren dat door veel linguisten uit de vorige eeuw (De Saussure, Firth, Harris) al werd voorgesteld als een fundamenteel principe om taal te verwerken en te genereren.

Momenteel leid ik het project Implicit Linguistics, dat ik heb opgezet op basis van een NWO Vici-beurs.

Projecten sinds 2001 (zie deze pagina voor een volledig overzicht sinds 1995)

• PoliticalMashup. Funded by NWO Humanities "Investeringssubsidies Middelgroot", 2010-2012. With the University of Amsterdam and the University of Groningen. Post-doc researcher: M. Reynaert.
• DutchSemCor. Funded by NWO Humanities "Investeringssubsidies Middelgroot", 2009-2011. With the Vrije Universiteit Amsterdam and the University of Amsterdam.  Scientific programmer: M. van Gompel.
• HITIME: Historical Timeline Mining and Extraction. Part of NWO CATCH: Continuous Access to Cultural Heritage. Funded by NWO, 2009-2013. Post-doc researcher: K. Zervanou, Ph.D. student: M. van de Camp, Scientific programmer: S. Hunt.
• SoNaR: STEVIN Dutch Reference Corpus, phases 1 and 2. Part of STEVIN: Spraak-en Taaltechnologische Essentiele voorzieningen in het Nederland, an NWO/FWO/EZ/OCW/AWI/IWT/Dutch Language Union Programme, 2007-2011. With partners from other Dutch and Flemish universities. Post-doc researchers: M. Reynaert, T. Gaustad van Zaanen.
  
• Implicit Linguistics. Funded by NWO Vici program, 2006-2011. Researchers: A. van den Bosch, H. Stehouwer (Ph.D. student), P. Berck (scientific programmer / Ph.D. student), M. van Zaanen (post-doc researcher), S. Wubben (Ph.D. student).
  
• Linguistic Data Quality Management. Funded by NWO HEFBOOM program, 2006-2008. Post-doc researcher: M. Reynaert.
• D-Coi: Dutch Corpus Initiative. Part of STEVIN: Spraak-en Taaltechnologische Essentiele voorzieningen in het Nederland, an NWO/FWO/EZ/OCW/AWI/IWT/Dutch Language Union Programme, 2005-2006. With partners from other Dutch and Flemish universities. Post-doc researcher: M. Reynaert.
• MITCH: Mining Information from Texts in Cultural Heritage. Part of NWO CATCH: Continuous Access to Cultural Heritage. Funded by NWO, 2005-2009. Researchers: C. Sporleder (until 2007), P. Lendvai (from 2007), M. van Erp, Scientific programmer: T. Porcelijn (until 2006), S. Hunt (from 2006).
• A-Propos: Pro-active personalization for professional document writing. Funded by the SenterNovem IOP-MMI (Innovative research programmes: Human-machine interaction) programme, 2004-2008. With L. Boves (Radboud University) and a consortium of Dutch language technology companies. Ph.D. student: T. Bogers.
• ROLAQUAD: Robust Language Understanding in Question-Answer Dialogues. Part of NWO IMIX: Interactive Multimodal Information Extraction. Funded by NWO, 2004-2008. With W. Daelemans, J. Zavrel (Textkernel B.V.), M. de Rijke (University of Amsterdam). Researchers: S. Canisius (Ph.D. student) and P. Lendvai (post-doc researcher).
  
• NEXTENS, Nederlandse Extensie voor Tekst naar Spraak. Funded by SST, Stichting Spraaktechnologie (Foundation for Speech Technology), 2002-2003. With T. Rietveld (KUN). Development and research: E. Marsi, J. Kerkhoff, A. Russell.
• VindIT: Combining visual and textual information for information retrieval. Funded by NWO ToKeN-2000 Programme, 2002-2005. With E.O. Postma (Universiteit Maastricht), L. Vuurpijl and E. Hoenkamp (Nijmegen University). Post-doc researcher: M. van Zaanen.
• Memory models of language. Funded by NWO Vernieuwingsimpuls programme, 2001-2005. Researchers: A. van den Bosch, I. Hendrickx (Ph.D. student), G.J. Busser (scientific programmer).
• PROSIT, Prosody from Information in Text. Funded by the joint NWO and FWO (Flanders Organisation for Scientific Research) Vlaams-Nederlands Comite voor Taal en Cultuur. 2

• Guest professor, Centre for Dutch Language and Speech, Faculty of Arts, University of Antwerp, Belgium, Jan 2005 - present.
  
• Visiting faculty, WhizBang! Labs Research, Pittsburgh, PA, USA, Sept-Dec 2001.

Programme committee membership:

• KNAW Computational Humanities Programme committee member
• NWO IMIX (GW/EW) Programme committee member
• NWO CATCH (EW/GW) Programme commitee member

Editorial board membership:

• Computational Linguistics (2003 - 2005)
• FoLLI Publications on Language, Logic, and Information (from 2005)
• Research on Language and Computation (2006 - 2011)

Awards:

• Best Explanation Award, AI Video Competition, AAAI-2007, Vancouver, CA, August 2007.
• Research Award 2002, Faculty of Arts, Tilburg University. With Hans Broekhuis and Ad Backus.
• SNS Limburg Award 1998, best Ph.D. thesis Universiteit Maastricht 1997?1998.

Ph.D. promotorship

• Sander Canisius, Structured prediction for natural language processing: A constraint satisfaction approach, Tilburg University, February 13, 2009. With second promotor Walter Daelemans.

Ph.D. co-promotorship

• Martin Reynaert, Text induced spelling correction, Tilburg University, December 2, 2005. With Walter Daelemans.
• Iris Hendrickx, Local classification and global estimation: Explorations of the k-nearest neighbor algorithm, Tilburg University, November 28, 2005. With Walter Daelemans.
• Piroska Lendvai, Extracting information from spoken input, TilburgUniversity, December 20, 2004. With Emiel Krahmer and Walter Daelemans.
• Laura Maruster, A machine learning approach to understand business processes, Eindhoven Technical University, August 27, 2003. With Hans Wortmann, Ton Weijters, and Walter Daelemans.
• Sabine Buchholz, Memory-based grammatical relations, Tilburg University, The Netherlands, December 13, 2002. With Walter Daelemans.

Current Ph.D. supervision

• Stephan Raaijmakers, Multinomial language learning: Investigations into the geometry of language. Scheduled defense date: December 1, 2009.
• Toine Bogers, Social tagging for recommendation and search. Scheduled defense date: December 8, 2009.
• Marieke van Erp, Soft and hard computing in ontological reasoning about natural history. Expected defense date: 2010.
• Herman Stehouwer, Memory-based text correction. Expected defense date: 2011.
• Peter Berck, Memory-based language modeling. Expected defense date: 2012.

A near-complete and up-to-date overview of my publications can be found here

.

• Chair of BNVKI-AIABN, Benelux Association for Artificial Intelligence
• Chair of STIL, Foundation for Inductive Learning Applications

• Member of the editorial board of Research on Language and Computation

• Program committee member of the NWO IMIX thematic program
• Program committee member of the NWO CATCH thematic program

Persoonlijke homepage