01378naa a2200205 i 4500 acta58962 20260224081030.0 190701s2016 hu o 100 eng d 978-963-306-450-4 SZTE Egyetemi Kiadványok Repozitórium hun eng Berend Gábor Utilizing word embeddings for part-of-speech tagging [elektronikus dokumentum] / Berend Gábor 2016 59-67 Magyar Számítógépes Nyelvészeti Konferencia 12 In this paper, we illustrate the power of distributed word representations for the part-of-speech tagging of Hungarian texts. We trained CRF models for POS-tagging that made use of features derived from the sparse coding of the word embeddings of Hungarian words as signals. We show that relying on such a representation, it is possible to avoid the creation of language specific features for achieving reliable performance. We evaluated our models on all the subsections of the Szeged Treebank both using MSD and universal morphology tag sets. Furthermore, we also report results for inter-subcorpora experiments. Nyelvészet - számítógép alkalmazása Magyar Számítógépes Nyelvészeti Konferencia (12.) (2016) (Szeged) http://acta.bibl.u-szeged.hu/58962/1/msznykonf_012_059-067.pdf Dokumentum-elérés