FAST COMPUTATION OF MAXIMUM ENTROPY/MINIMUM DIVERGENCE FEATURE GAIN

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  Printz, Harry ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ENTROPY; MODELING LANGUAGES;

BASE MODELS; FAST COMPUTATION; FEATURE FUNCTION; MAXIMUM-ENTROPY; MEMORY EFFICIENT; PREDICTIVE POWER; PROBABILITY MODELLING; SETS OF FEATURES; TRAINING CORPUS;

NATURAL LANGUAGE PROCESSING SYSTEMS;

EID: 85009148989     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. A. Berger, S. Della Pietra, V. Della Pietra, "A Maximum Entropy Approach to Natural Language Processing," Computational Linguistics, 22(1): 39-71, March 1996.
2. A. Berger, H. Printz, "A Comparison of Criteria for Maximum Entropy/Minimum Divergence Feature Selection," Proceedings of the Third Conference on Empirical Methods in Natural Language Processing, 97-106, Granada, Spain, June 1998. Available at www.cs.cmu.edu/"aberger/lm.html.
3. A. Berger, H. Printz, "Recognition Performance of a Large-Scale Dependency Grammar Language Model," Proceedings of the Fifth International Conference on Spoken Language Processing, Sydney, Australia, November 1998. Available at www.cs.cmu.edu/"aberger/lm.html.
4. S. Della Pietra, V. Della Pietra, and J. Lafferty, Inducing Features of Random Fields, Technical Report CMU-CS-95-144, School of Computer Science, Carnegie Mellon, Pittsburgh, PA, May 1995.