Homonymie mezi apelativy a proprii jako problém automatické morfologické analýzy češtiny
Homonymy among Czech common and proper nouns as the problem of automatic morphological analysis

Summary/Abstract: The aim of this paper is to provide a corpus-based analysis of one type of Czechproper nouns (type Zubří). We will argue that the adequate annotation (lemmatisationand morphological tagging) of proper nouns type Zubří depends on severalcircumstances:1) the coverage of the dictionary of the automatic analyser;2) the accurate description of the variability of inflexion forms;3) the non-trivial disambiguation of numerous homonymous word forms.We believe that while meeting the first two conditions is possible, the adequate disambiguationgoes beyond the possibilities of automatic morphological analysis.

• Details
• Contents