Výsledky vyhledávání - "András Hócza"

Learning Syntactic Tree Patterns From A Balanced Hungarian Natural Language Database, The Szeged Treebank

Autor: Kornél L. Kovács, C. Barta, János Csirik, Dóra Csendes, András Hócza, András Kocsor

Publikováno v: 2005 International Conference on Natural Language Processing and Knowledge Engineering.

The current paper has a twofold objective. On the one hand, it describes the creation and the features of the Szeged Treebank, which is currently the largest manually processed Hungarian textual database serving as a reference material for research i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fc9482d73ae90d1f95f286ceb3f09a05
https://doi.org/10.1109/nlpke.2005.1598739

Zobrazit plný text záznamu

Hungarian-English Machine Translation Using GenPar

Autor: András Hócza, András Kocsor

Publikováno v: Text, Speech and Dialogue ISBN: 9783540390909
TSD

We present an approach for machine translation by applying the GenPar toolkit on POS-tagged and syntactically parsed texts Our experiment in Hungarian-English machine translation is an attempt to develop prototypes of a syntax-driven machine translat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5ff1807519331238c1a54ebca7e032fb
https://doi.org/10.1007/11846406_11

Zobrazit plný text záznamu

Learning Syntactic Patterns Using Boosting and Other Classifier Combination Schemas

Autor: András Hócza, László Felföldi, András Kocsor

Publikováno v: Text, Speech and Dialogue ISBN: 9783540287896
TSD

This paper presents a method for the syntactic parsing of Hungarian natural language texts using a machine learning approach. This method learns tree patterns with various phrase types described by regular expressions from an annotated corpus. The PG

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bd6b9fa03b71cf505dcbe4c90f430a39
https://doi.org/10.1007/11551874_9

Zobrazit plný text záznamu

POS Tagging of Hungarian with Combined Statistical and Rule-Based Methods

Autor: András Hócza, János Csirik, András Kuba

Publikováno v: Text, Speech and Dialogue ISBN: 9783540230496
TSD

In this paper we will survey the key results achieved so far in Hungarian POS tagging. The most successful approaches have been selected and re-evaluated on a manually annotated corpus containing 1.2 million words. Tests were performed on single-doma

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bed634fe96fe6373c3910fe8b10701c3
https://doi.org/10.1007/978-3-540-30120-2_15

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání