Ph +31 13 466 3117
Fx +31 13 466 2892
Antal.vdnBosch (at) uvt.nl

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, and cultural heritage. My CV has more detailed information.

   

Writings & media

• Scientific publications
• Het volgende woord, inaugural address, Tilburg University, October 10, 2008 (animations shared on YouTube)
• The ILK group in the media
• Columns 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 (in Dutch) in Univers, Tilburg University's weekly
• Graphics

  

• STIL, treasurer
• BNVKI, chair

Current Ph.D. students: Peter Berck Matje van de Camp Marieke van Erp Herman Stehouwer Sander Wubben Post-doc researchers: Piroska Lendvai Martin Reynaert Kalliopi Zervanou Scientific programmers: Maarten van Gompel Ko van der Sloot Steve Hunt

Former (co-)supervised students: Toine Bogers, RSLIS, Copenhagen, Denmark Sabine Buchholz, Toshiba Research Europe Sander Canisius, The Netherlands Cancer Institute Iris Hendrickx, University of Antwerp Olga Houben-van Herwijnen, Tilburg University Piroska Lendvai, Tilburg University Laura Maruster, University of Groningen Martin Reynaert, Tilburg University Complete overview of current and former ILK members

Research projects

• Implicit Linguistics, Machine Learning of Text-to-Text Processing, an NWO Vici project.
• HiTiME, Historical Timeline Mining and Extraction, an NWO CATCH project
• MEMPHIX, Memory-based paraphrasing using implicit and explicit semantics
• Gezond Verstand, a student project on crowd sourcing Dutch common sense facts
• Past projects

Courses

• Digitaal Erfgoed (Digital Heritage), a BDM / ACM / HAIT-premaster Ba-level course, first semester 2008/2009
• Past courses, tutorials

Software

• Timbl: Tilburg memory-based learner.
• Mbmt: Memory-based machine translation.
• WOPR: Memory-based language modeling.
• Mbt: Memory-based tagger-generator and tagger.
• Dimbl: Distributed Timbl, parallel k-NN classification on multi-CPU machines
• Timpute: TiMBL-wrapper for internal database correction through imputation
• Fambl: Family-based learner, a generalized-example k-NN classifier. Reference guide.
• Tadpole: Dutch tagger-lemmatizer, morphological analyzer, and multi-word chunker.
• paramsearch: automatic parameter optimization for various machine learning algorithms.