Publication details

Type-based Search of Idiomatic Expression

Authors

BUŠTA Jan

Year of publication 2013
Type Article in Proceedings
Conference Seventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2013
MU Faculty or unit

Faculty of Informatics

Citation
Field Informatics
Keywords idioms; idiomatic candidates; syntactic fixedness; lexical fixedness; transitive verbs; thesaurus
Description This paper presents evaluation of different approaches to extract verb-noun idiomatic expressions in Czech. These approaches are based on the structure of the idiom and its behavior in language. PMI and syntactic and lexical fixedness modified using VerbaLex and generated thesaurus provide useful tool for choosing best idiomatic candidates for manual annotation and evaluation. Moreover we focused on general adapting the algorithms for Czech.
Related projects: