We report a word sense dis- ambiguation experiment on Italian verbs where both the sense inventory and the training data are derived from T-PAS, a lex- ical resource of typed predicate-argument structures grounded on corpora. We present a probabilistic model for sense dis- ambiguation that exploits the semantic fea- tures associated to each argument position of a verb.
Toward Disambiguating Typed Predicate-Argument Structures for Italian
Popescu, Octavian;Ngoc Phuoc An, Vo;Feltracco, Anna;Magnini, Bernardo
2014-01-01
Abstract
We report a word sense dis- ambiguation experiment on Italian verbs where both the sense inventory and the training data are derived from T-PAS, a lex- ical resource of typed predicate-argument structures grounded on corpora. We present a probabilistic model for sense dis- ambiguation that exploits the semantic fea- tures associated to each argument position of a verb.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
