An estimate of an upper bound for the entropy of English
Computational Linguistics
The art of computer programming, volume 1 (3rd ed.): fundamental algorithms
The art of computer programming, volume 1 (3rd ed.): fundamental algorithms
Context models in the MDL framework
DCC '95 Proceedings of the Conference on Data Compression
Generalizing case frames using a thesaurus and the MDL principle
Computational Linguistics
Local context selection for aligning sentences in parallel corpora
CONTEXT'07 Proceedings of the 6th international and interdisciplinary conference on Modeling and using context
Context-based sentence alignment in parallel corpora
CICLing'08 Proceedings of the 9th international conference on Computational linguistics and intelligent text processing
Hi-index | 0.00 |
We introduce three new techniques for statistical language models: extension modeling, nonmonotonic contexts, and the divergence heuristic. Together these techniques result in language models that have few states, even fewer parameters, and low message entropies.