Enhancing the Valency Dictionary of Czech Verbs: Tectogrammatical Annotation

Hana Skoumalová, Markéta Stranáková-Lopatková, Zdenek Zabokrtský

Abstract: A syntactic lexicon of verbs with the subcategorization information is crucial for NLP. Two phases of creating such lexicon are presented. The first phase consists of the automatic preprocessing of source data—particular valency frames are proposed. Where it is possible, the functors are assigned, otherwise the set of possible functors is proposed. In the second phase the proposed valency frames are manually refined.