Ágoston Nagy


2017

pdf bib
Language technology resources and tools for Mansi: an overview
Csilla Horváth | Norbert Szilágyi | Veronika Vincze | Ágoston Nagy
Proceedings of the Third Workshop on Computational Linguistics for Uralic Languages

2016

pdf bib
Where Bears Have the Eyes of Currant: Towards a Mansi WordNet
Csilla Horváth | Ágoston Nagy | Norbert Szilágyi | Veronika Vincze
Proceedings of the 8th Global WordNet Conference (GWC)

Here we report the construction of a wordnet for Mansi, an endangered minority language spoken in Russia. We will pay special attention to challenges that we encountered during the building process, among which the most important ones are the low number of native speakers, the lack of thesauri and the bear language. We will discuss our solutions to these issues, which might have some theoretical implications for the methodology of wordnet building in general.

2014

pdf bib
Szeged Corpus 2.5: Morphological Modifications in a Manually POS-tagged Hungarian Corpus
Veronika Vincze | Viktor Varga | Katalin Ilona Simkó | János Zsibrita | Ágoston Nagy | Richárd Farkas | János Csirik
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

The Szeged Corpus is the largest manually annotated database containing the possible morphological analyses and lemmas for each word form. In this work, we present its latest version, Szeged Corpus 2.5, in which the new harmonized morphological coding system of Hungarian has been employed and, on the other hand, the majority of misspelled words have been corrected and tagged with the proper morphological code. New morphological codes are introduced for participles, causative / modal / frequentative verbs, adverbial pronouns and punctuation marks, moreover, the distinction between common and proper nouns is eliminated. We also report some statistical data on the frequency of the new morphological codes. 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. According to the results, magyarlanc is able to achieve a state-of-the-art accuracy score on the 2.5 version as well.