no code implementations • LREC 2014 • Veronika Vincze, J{\'a}nos Zsibrita, P{\'e}ter Durst, Martina Katalin Szab{\'o}
In this paper we present the results of automatic error detection, concerning the definite and indefinite conjugation in the extended version of the HunLearner corpus, the learners corpus of the Hungarian language.
no code implementations • LREC 2014 • Veronika Vincze, Viktor Varga, Katalin Ilona Simk{\'o}, J{\'a}nos Zsibrita, {\'A}goston Nagy, Rich{\'a}rd Farkas, J{\'a}nos Csirik
The new version of the corpus made it possible to train magyarlanc, a data-driven POS-tagger of Hungarian on a dataset with the new harmonized codes.