| |
|
|
|
|
|
I have moved!
As of September 1, 2011, I am full professor
at Radboud University Nijmegen,
in Nijmegen, the Netherlands, within
the Centre for Language Studies
and CIW-Bedrijfscommunicatie of
the Faculty of Arts. I
used to be at the ILK Research Group
at Tilburg University, where I remain
a collaborator in various projects.
Research interests
In my research I develop machine learning and language
technology. Most of my work involves the intersection of the two
fields: computers that learn to understand and generate natural
language. Specific interests include memory-based learning, machine
translation, the relation between written and spoken language, text
mining, the Dutch language, computational humanities, and cultural heritage. My CV has more
detailed information.
Walter
Daelemans and I published a book entitled Memory-based language processing
(Cambridge University Press, 2005).
Writings & media
Current research projects
Recently finished: Implicit Linguistics, Machine Learning of Text-to-Text Processing, an NWO Vici project. Also see my other past projects.
|
|
|
|
|
|
|
|
|
|
|
|
Current Ph.D. students
Former (co-)supervised students
- Toine Bogers, IVA, Copenhagen, Denmark
- Sabine
Buchholz, Toshiba Research Europe
- Sander Canisius, The Netherlands Cancer Institute
- Marieke van Erp, Free University Amsterdam
- Iris Hendrickx, University of Lisboa
- Olga Houben-van Herwijnen, Tilburg University
- Piroska Lendvai, Hungarian Academy of Sciences
- Laura Maruster, University of Groningen
- Stephan Raaijmakers, TNO
- Herman Stehouwer, Max Planck Institut für Psycholinguistik Nijmegen
- Martin Reynaert, Tilburg University
Software
As part of past and ongoing projects I (co-)developed the following software:
- WOPR: Memory-based word prediction, language modeling, and spelling correction. Main developer: Peter Berck.
- Dimbl: Distributed Timbl, parallel k-NN classification on multi-CPU machines. Programmer: Ko van der Sloot.
- Timpute: TiMBL-wrapper for internal database correction through imputation. Programmer: Steve Hunt.
- paramsearch: automatic parameter optimization for various machine
learning algorithms.
- Fambl: Family-based learner, a generalized-example k-NN classifier. Reference guide.
- VALKUIL.net: Dutch spelling corrector. With Maarten van Gompel, Tanja Gaustad van Zaanen, and Monica Hajek.
- Frog: Dutch tagger-lemmatizer, morphological analyzer, and dependency parser. With the Frog development team.
I collaborated on the following software projects:
- Timbl: Tilburg memory-based learner.
- PBMBMT: Phrase-based memory-based machine translation.
- Mbt: Memory-based tagger-generator and tagger.
|
|
|
|
|
|
|
