Data mining: concepts and techniques
Data mining: concepts and techniques
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
Automatic verb classification based on statistical distributions of argument structure
Computational Linguistics
Generalizing case frames using a thesaurus and the MDL principle
Computational Linguistics
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Explaining away ambiguity: learning verb selectional preference with Bayesian networks
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Evaluating and combining approaches to selectional preference acquisition
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Disambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences
Computational Linguistics
Learning class-to-class selectional preferences
ConLL '01 Proceedings of the 2001 workshop on Computational Natural Language Learning - Volume 7
Hownet And the Computation of Meaning
Hownet And the Computation of Meaning
The minimum description length principle in coding and modeling
IEEE Transactions on Information Theory
A semi-supervised approach for key-synset extraction to be used in word sense disambiguation
AIRS'11 Proceedings of the 7th Asia conference on Information Retrieval Technology
Hi-index | 0.00 |
This paper proposes a semi-supervised approach for WSD in Word-Class based selectional preferences. The approach exploits syntagmatic and paradigmatic semantic redundancy in the semantic system and uses association computation and minimum description length for the task of WSD. Experiments on Predicate-Object collocations and Subject-Predicate collocations with polysemous predicates in Chinese show that the proposed approach achieves a precision which is 8% higher than the semantic-association based baseline. The semi-supervised nature of the approach makes it promising for constructing large scale selectional preference knowledge base.