In this paper, we propose innovative representations for automatic classification of verbs according to mainstream linguistic theories, namely VerbNet and FrameNet. First, syntactic and semantic structures capturing essential lexical and syntactic properties of verbs are defined. Then, we design advanced similarity functions between such structures, i.e., semantic tree kernel functions, for exploiting distributional and grammatical information in Support Vector Machines. The extensive empirical analysis on VerbNet class and frame detection shows that our models capture meaningful syntactic/semantic structures, which allows for improving the state-of-the-art. © 2012 Association for computational Linguistics.
Croce, D., Moschitti, A., Basili, R., Palmer, M. (2012). Verb classification using distributional similarity in syntactic and semantic structures. In 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference (pp.263-272).
Verb classification using distributional similarity in syntactic and semantic structures
CROCE, DANILO;MOSCHITTI, ALESSANDRO;BASILI, ROBERTO;
2012-07-01
Abstract
In this paper, we propose innovative representations for automatic classification of verbs according to mainstream linguistic theories, namely VerbNet and FrameNet. First, syntactic and semantic structures capturing essential lexical and syntactic properties of verbs are defined. Then, we design advanced similarity functions between such structures, i.e., semantic tree kernel functions, for exploiting distributional and grammatical information in Support Vector Machines. The extensive empirical analysis on VerbNet class and frame detection shows that our models capture meaningful syntactic/semantic structures, which allows for improving the state-of-the-art. © 2012 Association for computational Linguistics.File | Dimensione | Formato | |
---|---|---|---|
acl2012_v4.0.pdf
solo utenti autorizzati
Licenza:
Copyright dell'editore
Dimensione
270.27 kB
Formato
Adobe PDF
|
270.27 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.