Publication details
Propria (příjmení na -č) - problém automatické morfologické analýzy
| Title in English | Propria (Family Names on -č) - the Problem of the Automatic Morphological Analysis |
|---|---|
| Authors | |
| Year of publication | 2008 |
| Type | Article in Proceedings |
| Conference | Jazyk a jeho proměny |
| MU Faculty or unit | |
| Citation | |
| Field | Linguistics |
| Keywords | corpus; proprium; family name; authomatical morphological analysis |
| Description | The aim of this paper is to demonstrate how can be used the data mined from corpora for preparation of linguistic basis for NLP (natural language processing) applications. In three representative corpora of literary Czech (SYN2000, SYN2005, SYN2006PUB) the family names (animate masculine on č) were find. The possibility of verbal motivation of them was analyzed thereafter. In this way a list of evantual overgenerations of application of the word formation's formal rules (Osolsobě 2008) was enlarged. |
| Related projects: |