W
Walter Daelemans
Researcher at University of Antwerp
Publications - 463
Citations - 13831
Walter Daelemans is an academic researcher from University of Antwerp. The author has contributed to research in topics: Language technology & Natural language. The author has an hindex of 57, co-authored 444 publications receiving 12732 citations. Previous affiliations of Walter Daelemans include VU University Amsterdam & Radboud University Nijmegen.
Papers
More filters
Proceedings Article
Assessment of NER solutions against the first and second CALBC silver standard corpus
Dietrich Rebholz-Schuhmann,Antonio Jimeno-Yepes,Chen Li,Senay Kafkas,Ian Lewin,Ning Kang,Peter T. Corbett,David Milward,Ekaterina Buyko,Elena Beisswanger,Kerstin Hornbostel,Alexandre Kouznetsov,René Witte,Jonas B. Laurila,Christopher J. O. Baker,Cheng-Ju Kuo,Simon Clematide,Fabio Rinaldi,Richárd Farkas,György Móra,Kazuo Hara,Laura I. Furlong,Michael Rautschka,Mariana Neves,Alberto Pascual-Montano,Qi Wei,Nigel Collier,Md. Faisal Mahbub Chowdhury,Alberto Lavelli,Rafael Berlanga Llavori,Roser Morante,Vincent Van Asch,Walter Daelemans,José Luís Marina,Erik M. van Mulligen,Jan A. Kors,Udo Hahn +36 more
TL;DR: The first version of the Silver Standard Corpus (SSC-I) delivers a large set of annotations for a large number of documents and are sufficiently homogeneous to be reproduced with a trained classifier leading to an average F-measure of 85%.
Proceedings Article
Learning Dutch Coreference Resolution
Veronique Hoste,Walter Daelemans +1 more
TL;DR: This paper presents a machine learning approach to the resolution of coreferential relations between nominal constituents in Dutch, and proposes a modular approach in which a separate module is trained per NP type.
Proceedings ArticleDOI
A tool for the automatic creation, extension and updating of lexical knowledge bases
TL;DR: A tool is described which helps in the creation, extension and updating of lexical knowledge bases (LKBs) and at the knowledge level, constructors and filters can be defined.
Book ChapterDOI
Evaluating hybrid versus data-driven coreference resolution
TL;DR: The results show that by using the hybrid approach, one can reduce up to 92% of the training material without performance loss and the filters improve the overall precision of the classifiers leading to higher F-scores on the test set.