Publication at Faculty of Mathematics and Physics |
2023
Abstract
In light of the recent push for the creation and unification of large morphologically annotated resources, there is a call for (preferably language-independent, low-resource) methods of morph classification. This paper reports on a pilot experiment on morph classification of the Czech language.
We have performed two experiments - root morph recognition and complete morph classification. By exploiting simple quantitative methods and - in some cases - available Czech morphological resources, we have achieved morph-level precision of respectively 96.7% and 88.3%.