Courses and tutorials

Machine Learning, eight-week Tilburg/Eindhoven Ph.D. course, with Ton Weijters

Language technology: Machine learning of language - guest teacher, University of Antwerp, February - May 2006.

880409: Informatietechnologie (Information technology), with Emiel Krahmer

822025: Van tekst naar informatie (From text to information), with Sander Canisius

880414: Text mining, with Walter Daelemans, second semester (February-May), 2004-2005, Faculty of Arts, Tilburg University.
Website. Blackboard. Studiegids info.

810630: Taaltechnologie, with Emiel Krahmer, second block (November-December), 2004-2005, Faculty of Arts, Tilburg University.
Website. Blackboard. Studiegids info.

880409: Informatietechnologie, with Emiel Krahmer, second block (November-December), 2004-2005, Faculty of Arts, Tilburg University.
Website. Blackboard. Studiegids info.

Language technology: Machine learning of language - guest teacher, University of Antwerp, February - May 2004.

826164: Taal- en informatietechnologie, with Emiel Krahmer, first semester 2003-2004, Faculty of Arts, Tilburg University.
Website. Blackboard. Studiegids info.

ESSLLI 2003 Course on Memory-based language processing (restricted access), with Walter Daelemans, August 18-22, 2003, Vienna, Austria.

LOT Summer School 2003 Course on Memory-based analogical language processing (restricted access), June 23-27, 2003, Tilburg University.

827145: Lerende systemen, second semester 2002-2003, Faculty of Arts, Tilburg University.
Bi-annual course. Studiegids info.

826164: Taal- en informatietechnologie, with Emiel Krahmer, second semester 2002-2003, Faculty of Arts, Tilburg University.
Website.

Language technology: Machine learning of language - guest teacher, University of Antwerp, February - May 2003.

826164: Automatische bewerking en verwerking van informatie, with Emiel Krahmer, second semester 2001-2002, Faculty of Arts, Tilburg University.
Open website, restricted access website

Language technology: Machine learning of language - guest teacher, University of Antwerp, February - May 2002.

Capita selecta computerlinguistiek - guest teacher, University of Antwerp, February - May 2001. Theme of this 10-week course was Machine Learning.

ACL'99 Tutorial on Models of Memory and Analogy for Natural Language Learning and Processing (College Park MD, USA, June 1999)

ESSLLI'98 Course on Inductive Language Learning (Saarbruecken, Germany, August 1998)

Visual demos

A simple visual demo illustrating some of the basics of memory-based and decision-tree learning (work in progress)

My Ph.D. thesis, as briefly and visually as possible

Interactive memory-based language processing web-demos

The central ILK demo page lists a POS tagger demo for various languages, a shallow parser demo for English, and a demo of memory-based word sense disambiguation. These demos have all been developed within ILK, are memory-based, and run on TiMBL software.

TreeTalk, a word pronunciation demo, with (WAV or AU) speech output. The demo is developed by Bertjan Busser for his PhD project. It contains TreeTalk systems (IGTree decision trees trained on word-pronunciation pairs, performing both grapheme-phoneme conversion and stress assignment) for English and Dutch. The English data is the same as used in my PhD thesis. The speech synthesis is generated by the MBROLA diphone synthesiser.

MBMA, an experimental demo performing full morphosyntactic analysis of Dutch words. The underlying engine is a TiMBL server trained on Dutch wordform morphology from CELEX.

MBLEM, an experimental demo performing lemmatization of English, German, and Dutch words, trained on CELEX. As with MBMA, a TiMBL server drives the demo.

Media

One issue of Kwintessens, a popularising science programme on Dutch public television (Teleac-NOT), was devoted to our research. First broadcast was in April 2000. The Volkskrant published a condensed interview on 30 November 2002 (in Dutch).

Last update: 10 February 2005