Towards Czech Morphological Guesser

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors	ŠMERK Pavel
Year of publication	2008
Type	Article in Proceedings
Conference	Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2008
MU Faculty or unit	Faculty of Informatics
Citation
Web	RASLAN 2008 Workshop web page http://nlp.fi.muni.cz/raslan/2008/papers/10.pdf
Field	Informatics
Keywords	morphological guesser; morphological analysis; morphological guessing
Description	Paper presents a morphological guesser for Czech based on data from Czech morphological analyzer ajka. The idea behind the presented concept lies in a presumption that the new (and therefore unknown to the analyzer) words in a language behave quite regularly and that a description of this regular behaviour can be extracted from the existing data of the morphological analyzer. The paper describes both the construction of guesser data and the architecture of the guesser itself.
Related projects:	Centrum komputační lingvistiky Prostředky tvorby komplexní báze znalostí pro komunikaci se sémantickým webem v přirozeném jazyce