Abstract
If a corpus is submitted to a morphological analysis, there always remain some words that the analyser could not recognize (foreign names, misspellings,...). However, if a human reads the texts, he usually understands them, even if he does not knowas manywords as there are in the lexicon used by the morphological analyser. The language itself helps him to recognize unknown words. It is not only semantics or syntax but also pure morphology of unknown words that can contribute to their understanding.
In this article, I describe a “guesser” that can lower the amount of unrecognized words after the “classical” morphological analysis of the Czech texts. It was tested on the Czech National Corpus.
This research was supported by the GACR, Grant Nr. 405/96/K214.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kirschner, Zdeněk, MOSAIC-A Method of Automatic Extraction of Significant Terms from Texts. Faculty of Mathematics and Physics, Charles University, Prague 1983.
Hajič, Jan, Disambiguation of Rich Inflection (Computational Morphology of Czech), Karolinum Press, Praha 2001.
Chanod, Jean-Pierre, Tapanainen, Pasi, Creating a tagset, lexicon and guesser for a French tagger. In From Texts To Tags: Issues In Multilingual Language Analysis. pp.58–64. University College Dublin, Ireland 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hlaváčová, J. (2001). Morphological Guesser of Czech Words. In: Matoušek, V., Mautner, P., Mouček, R., Taušer, K. (eds) Text, Speech and Dialogue. TSD 2001. Lecture Notes in Computer Science(), vol 2166. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44805-5_9
Download citation
DOI: https://doi.org/10.1007/3-540-44805-5_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42557-1
Online ISBN: 978-3-540-44805-1
eBook Packages: Springer Book Archive