Improving trigram language modeling with the world wide web

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

Volumn 1, Issue , 2001, Pages 533-536

  Zhu, X ^a   Rosenfeld, R ^a  

^a Carnegie Mellon University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

N-GRAM; TRIGRAM LANGUAGE MODELING;

CONTEXT FREE GRAMMARS; PROBABILITY; SEARCH ENGINES; WORLD WIDE WEB;

SPEECH RECOGNITION;

EID: 0034852836     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Two decades of statistical language modeling: Where do we go from here?
2. Just-in-time language modeling
3. Improving trigram language modeling with the world wide web
4. Improved backing-off for m-gram language modeling
5. An empirical study of smoothing techniques for language modeling
6. Error-responsive modifications to speech recognizers: Negative N-grams
7. Evaluation metrics for language models
8. Adaptive language modeling using minimum discriminant estimation
9. A maximum entropy approach to natural language processing
10. Generalized iterative scaling for log-linear models
11. A Gaussian prior for smoothing maximum entropy models
12. 1998 TREC-7 spoken document retrieval track overview and results
13. Exponential language models, logistic regression, and semantic coherence