Three generative, lexicalised models for statistical parsing
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
An empirical study of smoothing techniques for language modeling
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Statistical parsing with a context-free grammar and word statistics
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
A generative probability model for unification-based grammars
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
The effect of corpus size in combining supervised and unsupervised training for disambiguation
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
| Hi-index | 0.01 |
Two general methods for the lexicalization of probabilistic grammars are presented which are modular, powerful and require only a small number of parameters. The first method multiplies the unlexicalized parse tree probability with the exponential of the mutual information terms of all word-governor pairs in the parse. The second lexicalization method accounts for the dependencies between the different arguments of a word. The model is based on a EM clustering model with word classes and selectional restrictions as hidden features. This model is useful for finding word classes, selectional restrictions and word sense probabilities.