Classes for fast maximum entropy training

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 561-564

  Goodman, J ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LANGUAGE MODELS; MAXIMUM ENTROPY TRAINING;

APPROXIMATION THEORY; MATHEMATICAL MODELS; PROBABILITY; SET THEORY; SPEECH RECOGNITION;

EQUIVALENCE CLASSES;

EID: 0034856455     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Generalized iterative scaling for log-linear models
2. Adaptive statistical language modeling: A maximum entropy approach
3. On structuring probabilistic dependencies in stochastic language modeling
4. Class-based n-gram models of natural language
5. Language model size reduction by pruning and clustering
6. Inducing features of random fields
7. Cluster expansions and iterative scaling for maximum entropy language models
8. Efficient training methods for maximum entropy language modeling
9. Putting it all together: Language model combination