Power law discounting for N-gram language models

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

Volumn , Issue , 2010, Pages 5178-5181

  Huang, Songfang ^a   Renals, Steve ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Absolute discount; Bayesian; Kneser Ney; Language model; Pitman Yor; Power law; Smoothing

Indexed keywords

SIGNAL PROCESSING;

ABSOLUTE DISCOUNT; BAYESIAN; KNESER-NEY; LANGUAGE MODEL; MODIFIED KNESER-NEY SMOOTHING; N-GRAM LANGUAGE MODELS; PITMAN-YOR; POWER-LAW; PROCESS LANGUAGES; SMOOTHING;

COMPUTATIONAL LINGUISTICS;

EID: 78049399782     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495007     Document Type: Conference Paper

References (13)

1. Stanley F. Chen and Joshua Goodman, "An empirical study of smoothing techniques for language modeling," Computer Speech & Language, vol. 13, no. 4, pp. 359-393, 1999.
2. Reinhard Kneser and Hermann Ney, "Improved backing-off form-gram language modeling," in Proc. of ICASSP'95, 1995, pp. 181-184.
3. Jesús Andrés-Ferrer and N. Ney, "Extensions of absolute discounting (Kneser-Ney method)," in Proc. of ICASSP '09, 2009, pp. 4729-4732.
4. Yee Whye Teh, "A hierarchical Bayesian language model based on Pitman-Yor processes," in Proc. of the Annual Meeting of the ACL, 2006, vol. 44.
5. Songfang Huang and Steve Renals, "Hierarchical Pitman-Yor language models for ASR in meetings," in Proc. of IEEE ASRU'07, Dec. 2007, pp. 124-129.
6. Songfang Huang and Steve Renals, "A parallel training algorithm for hierarchical Pitman-Yor process language models," in Proc. Interspeech'09, Sep. 2009.
7. Jim Pitman and Marc Yor, "The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator," The Annals of Probability, vol. 25, no. 2, pp. 855-900, 1997.
8. Sharon J. Goldwater, Thomas L. Griffiths, and Mark Johnson, "Interpolating between types and tokens by estimating power-law generators," in Proc. of NIPS 18, 2006.
9. David J. C. MacKay and Linda C. Bauman Peto, "A hierarchical Dirichlet language model," Natural Language Engineering, vol. 1, no. 3, pp. 1-19, 1994.
10. Yee Whye Teh, "A Bayesian interpretation of interpolated Kneser-Ney," Tech. Rep. TRA2/06, School of Computing, National University of Singapore, 2006.
11. Andreas Stolcke, "SRILM - an extensible language modeling toolkit," in Proc. of ICSLP'02, September 2002.
12. Thomas Hain, et al., "The AMI system for the transcription of speech in meetings," in Proc. of ICASSP'07, April 2007, pp. 357-360.
13. Vincent Wan and Thomas Hain, "Strategies for language model web-data collection," in Proc. of ICASSP'06, May 2006.