Impact of word classing on shrinkage-based language models

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 1804-1807

  Sarikaya, Ruhi ^a   Chen, Stanley F ^a   Sethy, Abhinav ^a   Ramabhadran, Bhuvana ^a  

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

Author keywords

Exponential models; Model M; Word classing

Indexed keywords

HUMAN COMPUTER INTERACTION; SHRINKAGE; SPEECH COMMUNICATION; TRANSLATION (LANGUAGES); COMPUTATIONAL LINGUISTICS; SYNTACTICS;

DIALOG SYSTEMS; EXPONENTIAL MODELS; N-GRAM MODELING; PART-OF-SPEECH TAGS; SPEECH-TO-SPEECH TRANSLATION; STATE INFORMATION; WORD CLASSING; WORD ERROR RATE; CLASS-BASED; LANGUAGE MODEL; MODEL M; N-GRAM MODELS; PART-OF-SPEECH TAGGER; PERFORMANCE;

COMPUTATIONAL LINGUISTICS; SHRINKAGE;

EID: 79959831916     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. M. Karahan, D. Hakkani-Tur, G. Riccardi, G. Tur, "Combining Classifiers for Natural Language Understanding", IEEE ASRU-2003, US Virgin Islands, Dec. 2003.
2. P. F. Brown, V. J. Della Pietra, P. V. deSouza, J. C. Lai and R.L. Mercer, "Class-based N-gram Models of Natural Language", Computational Linguistics, 18(4), pp: 467-479, 1992.
3. H. Schwenk, and J.L. Gauvain. "Using Continuous Space Language Models for Conversational Telephony Speech Recognition", IEEE Workshop on Spontaneous Speech Processing and Recognition, Tokyo, Japan, 2003.
4. S. F. Chen, "Performance Prediction for Exponential Language Models", Proc. of HLT/NAACL, Boulder, CO, 2009.
5. S. F. Chen, "Shrinking Exponential Language Models", Proc. of HLT/NAACL, Boulder, CO, 2009.
6. S. F. Chen, L. Mangu, B. Ramabhadran, R. Sarikaya and A. Sethy, "Scaling Shrinkage Based Language Models", Proc. of IEEE ASRU, Merano, Italy, 2009.
7. S. F. Chen, "Designing a Non-Finite-State Weighted Transducer Toolkit", Tech. Report, IBM Research Division, RC 24829, 2009.
8. J. Gimenez and L. Marquez, "SVMTool: A General POS-tagger Generator Based on Support Vector Machines", In Proc. LREC-04, 2004.
9. Y. Gao, L. Gu, B. Zhou, R. Sarikaya, H.-K. Kuo. A.-V.I. Rosti, M. Afify, W. Zhu, "IBM MASTOR: Multilingual Automatic Speech-to-Speech Translator", Proc. of ICASSP, Toulouse, France, 2006.
10. S. Chen, J. Goodman, "An Empirical Study of Smoothing Techniques for Language Modeling", ACL, Santa Cruz, CA, 1996.
11. C. Chelba and F. Jelinek, "Structured language modeling", Computer Speech and Language, 14(4), 283-332, 2000.
12. A. Emami and P. Xu and F. Jelinek, "Using a Connectionist Model in a Syntactical based Language Model", Proc. of IEEE ICASSP, v. 1, 372-375, Hong Kong, 2003.
13. H. Erdogan, R. Sarikaya, S.F. Chen, Y. Gao and M. Picheny, "Using Semantic Analysis to Improve Speech Recognition Performance", Computer Speech & Language Journal, vol. 19(3), pp: 321-343, 2005. (Pubitemid 40467094)
14. C. Samuelsson and W. Reichl, "A class-based language model for large-vocabulary speech recognition extracted from part-of-speech statistics", In Proc. of ICASSP, pp: 537-540, 1999.
15. P. A. Heeman, "POS tags versus classes in language modeling", In Proc. of Sixth Workshop on Very Large Corpora, 1998.
16. L. Galescu and E. Ringger, "Augmenting Words with Linguistic Information for N-Gram Language Models", In Proc. of Eurospeech, pp: 537-540, 1999.
17. J. Cui, Y. Su, K. Hall, and F. Jelinek, "Investigating linguistic knowledge in a maximum entropy token-based language model", In Proc. of ASRU, pp: 171-176, 2007.