Unsupervised language model adaptation via topic modeling based on named entity hypotheses

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

Volumn , Issue , 2008, Pages 4921-4924

  Liu, Yang ^a   Liu, Feifan ^a  

^a UNIVERSITY OF TEXAS AT DALLAS   (United States)

Author keywords

Clustering; Language model adaptation; Latent dirichlet allocation (LDA); Named entities; Rescoring

Indexed keywords

ACOUSTICS; COMPUTER NETWORKS; LINGUISTICS; SIGNAL PROCESSING; SPEECH;

CLUSTERING; LANGUAGE MODEL ADAPTATION; LATENT DIRICHLET ALLOCATION (LDA); NAMED ENTITIES; RESCORING;

LAGRANGE MULTIPLIERS;

EID: 51449102392     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518761     Document Type: Conference Paper

References (16)

1. R. Iyer and M. Ostendorf, "Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models," in Proc. of ICSLP, 1996.
2. J. Bellegarda, "Exploiting latent semantic information in statistical language modeling," IEEE Transactions on Speech and Audio Processing, vol. 88(80), 2000.
3. D. Gildea and T. Hofmann, "Topic-based language models using EM," in Proc. of Eurospeech, 1999.
4. D. Blei, A. Ng, and M. Jordan, "Latent Dirichlet allocation," Journal of Machine Learning Research, vol. 3, pp. 993-1022, 2003.
5. F. Liu and Y. Liu, "Unsupervised language model adaptation incorporating named entity information," in Proc. of ACL, 2007.
6. R. Kuhn and R.D. Mori, "A cache-based natural language model for speech recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, pp. 570-583, 1990.
7. R. Rosenfeld, "A maximum entropy approach to adaptive statistical language modeling," Computer, Speech and Language, vol. 10, pp. 187-228, 1996.
8. Y.C. Tam and T. Schultz, "Dynamic language model adaptation using variational Bayes inference," in Proc. of INTERSPEECH, 2005.
9. P. Hsu and J. Glass, "Style & topic language model adaptation using HMM-LDA," in Proc. of EMNLP, 2006, pp. 373-381.
10. D. Mrva and P.C. Woodland, "Unsupervised language model adaptation for Mandarin broadcast conversation transcription," in Proc. of INTERSPEECH, 2006, pp. 2206-2209.
11. A. Heidel, H. Chang, and L. Lee, "Language model adaptation using latent dirichlet allocation and an efficient topic inference algorithm," in Proc. of Interspeech, 2007.
12. T. Griffiths, M. Steyvers, D. Blei, and J. Tenenbaum, "Integrating topics and syntax," Adv. in Neural Information Processing Systems, vol. 17, pp. 537-544, 2004.
13. G. Karypis, "Software for clustering high-dimensional datasets," http://glaros.dtc.umn.edu/gkhome/views/cluto.
14. M. Hwang, X. Lei, W. Wang, and T. Shinozaki, "Investigation on Mandarin broadcast news speech recognition," in Proc. of Interspeech, 2006.
15. H. Ji and R. Grishman, "Improving nametagging by reference resolution and relation detection," in Proc. of ACL, 2005, pp. 411-418.
16. A. Stolcke, "SRILM - an extensible language modeling toolkit," in Proc. of ICSLP, 2002.