Computer Science – Computation and Language
Scientific paper
2001-09-18
Proceedings of the Workshop "Computational Natural Language Learning" (CoNLL-2001). In conjunction with ACL'2001/EACL'2001. To
Computer Science
Computation and Language
Scientific paper
Selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This papers extends previous statistical models to class-to-class preferences, and presents a model that learns selectional preferences for classes of verbs. The motivation is twofold: different senses of a verb may have different preferences, and some classes of verbs can share preferences. The model is tested on a word sense disambiguation task which uses subject-verb and object-verb relationships extracted from a small sense-disambiguated corpus.
Agirre Eneko
Martinez Daniel
No associations
LandOfFree
Learning class-to-class selectional preferences does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Learning class-to-class selectional preferences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning class-to-class selectional preferences will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-424897