Paper: Verbal Valency Frame Detection and Selection in Czech and English

ACL ID W14-2902
Title Verbal Valency Frame Detection and Selection in Czech and English
Venue Workshop on Events: Definition, Detection, Coreference, and Representation
Session
Year 2014
Authors

We present a supervised learning method for verbal valency frame detection and se- lection, i.e., a specific kind of word sense disambiguation for verbs based on subcat- egorization information, which amounts to detecting mentions of events in text. We use the rich dependency annotation present in the Prague Dependency Tree- banks for Czech and English, taking ad- vantage of several analysis tools (taggers, parsers) developed on these datasets pre- viously. The frame selection is based on manually created lexicons accompanying these treebanks, namely on PDT-Vallex for Czech and EngVallex for English. The re- sults show that verbal predicate detection is easier for Czech, but in the subsequent frame selection task, better results have been achieved for English.