Class-Based Construction of a Verb Lexicon
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Using semantically motivated estimates to help subcategorization acquisition
EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
Constructing conceptual graphs using linguistic resources
TELE-INFO'05 Proceedings of the 4th WSEAS International Conference on Telecommunications and Informatics
Extended lexical-semantic classification of English verbs
CLS '04 Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics
Hi-index | 0.00 |
The paper describes the implementation of the Levin's syntactic-semantic classification of English verbs onto verbs in Croatian language. The current Croatian valence verb lexicon (CROVALLEX) containing 1739 verbs associated with 5118 valence frames was enriched with 72 broad semantic classes with two further levels of subdivision (173 classes in total). The research results show that such classification helps in capturing the relation between the syntax and semantics of Croatian verbs in order to reduce the redundancy in the lexicon, but they also show that Levin's classification does not provide a means for full inference of the verb semantics on the basis of its syntactic behavior for Croatian language. The research brought us to conclusion that we need to introduce the more distinctive semantic roles.