Research Group for Language Technology

Starting Page > Departments > Department of Language Technology and Sociolinguistics > Research Group for Language Technology > Selected Publications

Selected Publications

Novák, Attila, Viktor Nagy, and Csaba Oravecz. 2003. Corpus assisted development of a Hungarian morphological analyser and guesser. In Proceedings of the Corpus Linguistics 2003 Conference, 583-590. Lancaster.

Oravecz, Csaba and Péter Dienes. 2002. Efficient Stochastic Part-of-Speech tagging for Hungarian. In Proceedings of the Third International Conference on Language Resources and Evaluation, 710-717. Las Palmas.

Dan Tufiş, Péter Dienes, Csaba Oravecz, and Tamás Váradi. 2000. Principled hidden tagset design for tiered tagging of Hungarian. In Proceedings of the Second International Conference on Language Resources and Evaluation, 1421-1426. Athens.

Dienes, Péter and Csaba Oravecz. 2000. Bottom-up tagset design from maximally reduced tagset. In Proceedings of the Workshop on Linguistically Interpreted Corpora, COLING 2000, ed. by Anne Abeille, Thorsten Brants, and Hans Uszkoreit, 42-47.

Zoltán Alexin, Tamás Váradi, Csaba Oravecz, Gábor Prószéky, János Csirik, and Tibor Gyimóthy. 1999. FGT - a framework for generating rule-based taggers. In ILP-99 Late-Breaking papers. Bled, Slovenia.

Oravecz, Csaba and Tamás Váradi. 1999. Developing the Hungarian concise dictionary into a lexical database. In Papers in Computational Lexicography, COMPLEX'99, 229-236. Budapest: Research Institute for Linguistics.

Váradi, Tamás and Csaba Oravecz. 1999. Morphosyntactic ambiguity and tagset design for Hungarian. In Proceedings of the Workshop on Linguistically Interpreted Corpora, EACL'99, 8-13. Bergen: Association for Computational Linguistics.

Gábor Kata, Héja Enikő: Clustering Hungarian Verbs on the Basis of Complementation Patterns. In: Proceedings of the ACL'07 Conference, Prague, 2007

Gábor Kata: Syntactic Parsing and Named Entity Recognition for Hungarian with Intex. In: S. Koeva, D. Maurel, M. Silberztein (szerk.): Formaliser les langues avec l'ordinateur: De Intex à Nooj, Presses Universitaires de Franche-Comté, Besançon, 2007., pp. 353-366.

Ágnes Gyarmati and Dániel Vásárhelyi: Unsupervised Categorization of Phonemes. In: P. Osenova, E. Hinrichs and J. Nerbonne (eds.) Proceedings - Computational Phonology Workshop at RANLP, Borovets, pp. 33-36, 2007.

Kuti J., Varasdi, K., Gyarmati, Á., Vajda, P.: Hungarian WordNet and representation of verbal event structure. In: Acta Cybernetica, 18(2), 2007, 315-328.  

Péter Halácsy, András Kornai, Csaba Oravecz: HunPos - an open source trigram tagger. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, Companion Volume: Proceedings of the Demo and Poster Sessions, Association for Computational Linguistics, Prague, Czech Republic, pages 209-212, 2007.  

Miháltz Márton, Naszódi Mátyás, Vajda Péter, Varasdi Károly NP-koreferenciák feloldása magyar szövegekben a Magyar WordNet ontológia segítségével. [NP-coreference resolution in Hungarian texts using the Hungarian WordNet] In: Tanács A., Csendes D. (szerk.): V. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY2007) [Proceedings of the V. Hungarian Computational Linguistics Conference. MSZNY 2007] SZTE, Szeged, 2007, p. 138-146.

Sass, Bálint: First attempt to automatically generate Hungarian semantic verb classes. In: Davies, M., Rayson, P., Hunston, S., Danielsson, P. (eds.): Proceedings of the 4th Corpus Linguistics Conference, Birmingham, 2007.  

Sass Bálint: ,,Mazsola'' - eszköz a magyar igék bővítményszerkezetének vizsgálatára. ["Mazsola" - A tool for investigating the argument structure of Hungarian verbs.] In: Váradi Tamás (szerk.): I. Alkalmazott Nyelvészeti Doktorandusz Konferencia kötete [Proceedings of the 1st Applied Linguistics PhD Conference.] MTA Nyelvtudományi Intézet, Budapest, 2007, p. 137-149.  

Váradi T, Kiss G: Equivalence and Non-equivalence in Parallel Corpora. In: Wolfgang Teubert (szerk) Text corpora and Multilingual Lexicography. Benjamins, Amsterdam/Philadelphia, 2007, pp. 147-157  

Váradi T: Fishing for translation equivalents using grammatical anchors. In: Wolfgang Teubert, Ramesh Krishnamurthy (szerk.) Corpus Linguistics: Critical Concepts in Linguistics. Routledge, 2007, pp. 299-312  

Váradi T: NP Modification Structures in Parallel Corpora. In: Gunella Anderman and Margaret Rogers (szerk.) Incorporating Corpora. The Linguist and the Translator. Multilingual Matters Ltd, Clevedon/Buffalo/Toronto, 2007, pp. 168-187.  

Váradi T: Rule-Based Partial MT Using Enhanced Finite-State Grammars in NooJ. In: Z. Kedad et al.(szerk.): NLDB 2007, Lecture Notes in Computer Science 4592, Springer-Verlag Berlin Heidelberg 2007, pp. 376-381.

Gábor, K., Héja E., Kuti J., Nagy V., Váradi T.: A lexikon a nyelvtechnológiában. [The lexicon in language technology.] In: Kiefer Ferenc (szerk.) Strukturális magyar nyelvtan IV. A lexikon szerkezete. [A Structural Grammar of Hungarian IV. The Lexicon.] Akadémiai Kiadó, Budapest, 2008, p. 853-893.  

Kuti, J., Varasdi, K., Gyarmati, Á., Vajda, P.: Language independent and language dependent innovations in the Hungarian WordNet. In: Tanács, A., Csendes, D., Vincze, V., Fellbaum, Ch., Vossen, P. (eds.): Proceedings of the IVth Global WordNet Conference, 2008, 254-269.

Miháltz, M., Hatvani, Cs., Kuti, J., Szarvas, Gy., Csirik, J., Prószéky, G., Váradi, T.: Methods and Results of the Hungarian WordNet Project. In: Tanács, A., Csendes, D., Vincze, V., Fellbaum, Ch., Vossen, P. (eds.): Proceedings of the IVth Global WordNet Conference, 2008, 311-321.

Sass, Bálint.: The Verb Argument Browser. In: Sojka, P., Horák, A., Kopecek, I., Pala, K. (eds.): 11th International Conference on Text, Speech and Dialog, TSD 2008, Brno, Csehország, 2008, Proceedings. Lecture Notes in Computer Science 5246, pp. 187-192.

Back