Self-organized language modeling for speech recognition
Readings in speech recognition
Explanation-Based Generalization: A Unifying View
Machine Learning
Machine Learning
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
A speech to speech translation system built from standard components
HLT '93 Proceedings of the workshop on Human Language Technology
Experiments with corpus-based LFG specialization
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Experiments with Learning Parsing Heuristics
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Some novel applications of Explanation-Based Learning to parsing Lexicalized Tree-Adjoining Grammars
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Fast parsing using pruning and grammar specialization
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
The use of instrumentation in grammar engineering
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Open Systems & Information Dynamics
Corpus-based grammar specialization
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Hi-index | 0.00 |
Explanation-based generalization is used to extract a specialized grammar from the original one using a training corpus of parse trees. This allows very much faster parsing and gives a lower error rate, at the price of a small loss in coverage. Previously, it has been necessary to specify the tree-cutting criteria (or operationality criteria) manually; here they are derived automatically from the training set and the desired coverage of the specialized grammar. This is done by assigning an entropy value to each node in the parse trees and cutting in the nodes with sufficiently high entropy values.