Automatic labeling of semantic roles
Computational Linguistics
A maximum-entropy-inspired parser
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Automatic retrieval and clustering of similar words
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Semantic classes and syntactic ambiguity
HLT '93 Proceedings of the workshop on Human Language Technology
Dependency-Based Construction of Semantic Space Models
Computational Linguistics
Towards robust semantic role labeling
Computational Linguistics
Combination strategies for semantic role labeling
Journal of Artificial Intelligence Research
Generalizing over lexical features: selectional preferences for semantic role classification
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Introduction to the CoNLL-2005 shared task: semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
A Bayesian model for unsupervised semantic parsing
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Verb classification using distributional similarity in syntactic and semantic structures
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Investigating the semantics of frame elements
EKAW'12 Proceedings of the 18th international conference on Knowledge Engineering and Knowledge Management
| Hi-index | 0.00 |
This work incorporates Selectional Preferences (SP) into a Semantic Role (SR) Classification system. We learn separate selectional preferences for noun phrases and prepositional phrases and we integrate them in a state-of-the-art SR classification system both in the form of features and individual class predictors. We show that the inclusion of the refined SPs yields statistically significant improvements on both in domain and out of domain data (14.07% and 11.67% error reduction, respectively). The key factor for success is the combination of several SP methods with the original classification model using meta-classification.