article

Task adaptation in stochastic language model for Chinese homophone disambiguation

Author:

Yue-Shi LeeAuthors Info & Claims

ACM Transactions on Asian Language Information Processing (TALIP), Volume 2, Issue 1

Pages 49 - 62

https://doi.org/10.1145/964161.964164

Published: 01 March 2003 Publication History

Abstract

The runtime application domain has a great effect on the performance of practical corpus-based applications. Previous smoothing techniques and class-based and similarity-based models could not handle the dynamic status perfectly. In this paper, an adaptive learning algorithm is proposed for task adaptation that best fits the runtime application domain in applying Chinese homophone disambiguation. The proposed algorithm is first formulated by a neural network model and then generalized to avoid the problem of slow convergence. The resulting techniques are greatly simplified and robust. The experimental results demonstrate the effects of the learning algorithm from a generic domain to a specific one. A methodology is also presented to show how these techniques can be extended to various language models and corpus-based applications.

References

[1]

BROWN, P. F., ET AL. 1992. Class-based N-gram models of natural language. Comput. Linguist. 18, 467--479.]]

[2]

CHURCH, K. W., AND GALE, W. A. 1991. A comparison of the enhanced good-Turing and deleted estimation methods for estimating probabilities of English bigrams. Comput. Speech Lang. 5, 19--54.]]

[3]

DAGAN, I. ET AL. 1994. Similarity-based estimation of word cooccurrence probabilities. In Proceedings of the 32nd Annual Meeting of ACL. 272--278.]]

[4]

ESSEN, U. AND STEINBISS, V. 1992. Cooccurrence smoothing for stochastic language modeling. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. I-161--I-164.]]

[5]

FURUL, S. ET AL. 1992. Recent topics in speech recognition research at NTT laboratories. In Proceedings of Speech and Natural Language Workshop. 162--167.]]

[6]

GOOD, I. J. 1953. The population frequencies of species and the estimation of population parameters. Biometrika 40. 237--264.]]

[7]

KATZ, S. M. 1987. Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Trans. Acoustic, Speech, Signal Process. 35. 400--401.]]

[8]

KONCAR, N. AND GUTHRIE, G. 1994. A natural language translation neural network. In Proceedings of the International Conference on New Methods in Language Processing. 71--77.]]

[9]

KUHN, R. AND MORI, R. D. 1990. A cache-based natural language model for speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12, 570--583.]]

[10]

KUHN, R. AND MORI, R. D. 1992. Corrections to a cache-based natural language model for speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. 14. 691--692.]]

[11]

LIN, Y. C. ET AL. 1994. Automatic model refinement: with an application to tagging. In Proceedings of the International Conference on Computational Linguistics. 148--153.]]

[12]

MATSUNAGA, S. ET AL. 1992. Task adaptation in stochastic language models for continuous speech recognition. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. I-165--I-168.]]

[13]

NAKAMURA, M. ET AL. 1990. Neural network approach to word category prediction for English texts. In Proceedings of the International Conference on Computational Linguistics. 213--218.]]

[14]

PEREIRA, F. ET AL. 1993. Distributional clustering of English words. In Proceedings of the 31st Annual Meeting of ACL. 183--190.]]

[15]

PLACEWWAY, P. ET AL. 1993. The estimation of powerful language models from small and large corpora. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. II-33-II-36.]]

[16]

SCHMID, H. 1987. Part-of-speech tagging with neural networks. In Proceedings of the International Conference on Computational Linguistics. 172--176.]]

[17]

SHIKANO, K. 1987. Improvement of word recognition results by trigram model. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. 1261--1264.]]

[18]

SPROAT, R. 1990. An application of statistical optimization with dynamic programming to phonemic-input-to-character conversion for Chinese. In Proceedings of the ROCLING Conference. 377--390.]]

[19]

WONG, S. K. M. AND CAI, Y. J. 1993. Computation of term associations by a neural network. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 107--115.]]

Cited By

Schuppler BSchrank T(2018)On the use of acoustic features for automatic disambiguation of homophones in spontaneous GermanComputer Speech & Language10.1016/j.csl.2017.12.01152(209-224)Online publication date: Nov-2018
https://doi.org/10.1016/j.csl.2017.12.011
Wen JWang XXu WJiang H(2008)Ambiguity solution of pinyin segmentation in continuous Pinyin-to-Character conversion2008 International Conference on Natural Language Processing and Knowledge Engineering10.1109/NLPKE.2008.4906775(1-7)Online publication date: Oct-2008
https://doi.org/10.1109/NLPKE.2008.4906775
Tsai J(2006)Using word support model to improve Chinese input systemProceedings of the COLING/ACL on Main conference poster sessions10.5555/1273073.1273181(842-849)Online publication date: 17-Jul-2006
https://dl.acm.org/doi/10.5555/1273073.1273181
Show More Cited By

Index Terms

Task adaptation in stochastic language model for Chinese homophone disambiguation
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing

Recommendations

Word category disambiguation for malayalam: a language model approach
CCSEIT '12: Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology

In this paper we are introducing a new method of word category disambiguation for Malayalam language. The proposed model is a supervised Machine learning system. It consists of a language model, which is trained by an annotated corpus of 10,000 words. ...
Comparison of performance of enhanced morpheme-based language model with different word-based language models for improving the performance of Tamil speech recognition system

This paper describes a new technique of language modeling for a highly inflectional Dravidian language, Tamil. It aims to alleviate the main problems encountered in processing of Tamil language, like enormous vocabulary growth caused by the large number ...
Multi class-based n-gram language model for new words using web data
ROCOM'11/MUSP'11: Proceedings of the 11th WSEAS international conference on robotics, control and manufacturing technology, and 11th WSEAS international conference on Multimedia systems & signal processing

Out-of-vocabulary (OOV) words cause a serious problem for automatic speech recognition (ASR) system. Not only it will be miss-recognized as an in-vocabulary word with similar phonetics, but the error will also affect nearby words to make errors. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Transactions on Asian Language Information Processing

ACM Transactions on Asian Language Information Processing Volume 2, Issue 1

March 2003

77 pages

ISSN:1530-0226

EISSN:1558-3430

DOI:10.1145/964161

Issue’s Table of Contents

Copyright © 2003 ACM.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 March 2003

Published in TALIP Volume 2, Issue 1

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
226
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)2

Reflects downloads up to 18 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Schuppler BSchrank T(2018)On the use of acoustic features for automatic disambiguation of homophones in spontaneous GermanComputer Speech & Language10.1016/j.csl.2017.12.01152(209-224)Online publication date: Nov-2018
https://doi.org/10.1016/j.csl.2017.12.011
Wen JWang XXu WJiang H(2008)Ambiguity solution of pinyin segmentation in continuous Pinyin-to-Character conversion2008 International Conference on Natural Language Processing and Knowledge Engineering10.1109/NLPKE.2008.4906775(1-7)Online publication date: Oct-2008
https://doi.org/10.1109/NLPKE.2008.4906775
Tsai J(2006)Using word support model to improve Chinese input systemProceedings of the COLING/ACL on Main conference poster sessions10.5555/1273073.1273181(842-849)Online publication date: 17-Jul-2006
https://dl.acm.org/doi/10.5555/1273073.1273181
Wang XLu Li Yao LAnwar W(2006)A Maximum Entropy Approach to Chinese Pin Yin-To-Character Conversion2006 IEEE International Conference on Systems, Man and Cybernetics10.1109/ICSMC.2006.384567(2956-2959)Online publication date: Oct-2006
https://doi.org/10.1109/ICSMC.2006.384567

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents