Abstract
In case of morphologically rich languages, full morphological disambiguation is a fundamental task that is more difficult than just providing PoS tags. In our paper, we overview Hungarian morphological disambiguation tools, and evaluate some common tagger combination techniques in order to improve annotation accuracy. Following an error analysis of the existing tools, we introduce a method that independently selects the proper tag and lemma and harmonizes them achieving a 28.90% error rate reduction compared to PurePos, a state-of-the-art Hungarian morphological annotation tool.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Machine Learning 6(1), 37–66 (1991)
Brill, E., Wu, J.: Classifier combination for improved lexical disambiguation. In: Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, vol. 1, pp. 191–195. Association for Computational Linguistics, Stroudsburg (1998)
Csendes, D., Csirik, J., Gyimóthy, T.: The Szeged Corpus: A POS tagged and syntactically annotated Hungarian natural language corpus. In: Proceedings of the 5th International Workshop on Linguistically Interpreted Corpora LINC 2004 at The 20th International Conference on Computational Linguistics COLING 2004, pp. 19–23 (2004)
Hajič, J., Krbec, P., Květoň, Oliva, K., Petkevič, V.: Serial combination of rules and statistics: A case study in Czech tagging. In: Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, pp. 268–275. Association for Computational Linguistics (2001)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software. ACM SIGKDD Explorations Newsletter 11(1), 10 (2009)
Van Halteren, H., Zavrel, J., Daelemans, W.: Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems. Computational Linguistics 27(2), 199–229 (2001)
Laki, L.: Investigating the Possibilities of Using SMT for Text Annotation. In: Simões, A., Queirós, R., da Cruz, D. (eds.) 1st Symposium on Languages, Applications and Technologies. OpenAccess Series in Informatics (OASIcs), vol. 21, pp. 267–283. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, Dagstuhl (2012)
Orosz, G., Novák, A.: PurePos – an open source morphological disambiguator. In: Sharp, B., Zock, M. (eds.) Proceedings of the 9th International Workshop on Natural Language Processing and Cognitive Science, Wroclaw, pp. 53–63 (2012)
Prószéky, G.: Industrial applications of unification morphology. Association for Computational Linguistics, Morristown (1994)
Prószéky, G., Novák, A.: Computational Morphologies for Small Uralic Languages. In: Inquiries into Words, Constraints and Contexts, Stanford, California, pp. 150–157 (2005)
Trón, V., Halácsy, P., Rebrus, P., Rung, A., Vajda, P., Simon, E.: Morphdb.hu: Hungarian lexical database and morphological grammar. In: Proceedings of the Fifth Conference on International Language Resources and Evaluation, Genoa, pp. 1670–1673 (2006)
Witten, I.H., Frank, E., Hall, M.A.: Data Mining: Practical Machine Learning Tools and Techniques, 3rd edn. (2011)
Zsibrita, J., Vincze, V., Farkas, R.: magyarlanc 2.0: szintaktikai elemzés és felgyorsított szófaji egyértelműsítés. In: IX. Magyar Számítógépes Nyelvészeti Konferencia, pp. 238–374. Szegedi Tudományegyetem, Szeged (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Orosz, G., Laki, L.J., Novák, A., Siklósi, B., Wenszky, N. (2013). Improved Hungarian Morphological Disambiguation with Tagger Combination. In: Habernal, I., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2013. Lecture Notes in Computer Science(), vol 8082. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40585-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-40585-3_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40584-6
Online ISBN: 978-3-642-40585-3
eBook Packages: Computer ScienceComputer Science (R0)