Automatic Verse Processing for the Corpus of Czech Verse and Beyond

Abstrakt

This paper presents the algorithms of the verse processing system KVĚTA that was developed for the Corpus of Czech Verse (http://versologie.cz/en). The core of this system comprises components providing annotation of rhythm, meter and rhyme.

As these features strongly depend on the language of the respective texts, this paper is especially interested in methods for the annotation of rhyme and in their applicability to the analysis of texts across languages.

Klíčová slova

• versification
• corpus linguistics