Lexical triggers and latent semantic analysis for cross-lingual language model adaptation

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

Lexical triggers and latent semantic analysis for cross-lingual language model adaptation

Full text

Pdf (256 KB)

Source

ACM Transactions on Asian Language Information Processing (TALIP) archive
Volume 3 , Issue 2 (June 2004) table of contents

Pages: 94 - 112

Year of Publication: 2004

ISSN:1530-0226

Authors

Woosung Kim	The Johns Hopkins University, Baltimore, MD
Sanjeev Khudanpur	The Johns Hopkins University, Baltimore, MD

Publisher

ACM New York, NY, USA

Bibliometrics

Downloads (6 Weeks): 6, Downloads (12 Months): 41, Citation Count: 0

Additional Information:

abstract references index terms collaborative colleagues

Tools and Actions:	Request Permissions Review this Article Save this Article to a Binder Display Formats: BibTeX EndNote ACM Ref

DOI Bookmark:	Use this link to bookmark this Article: http://doi.acm.org/10.1145/1034780.1034782 What is a DOI?

ABSTRACT

In-domain texts for estimating statistical language models are not easily found for most languages of the world. We present two techniques to take advantage of in-domain text resources in other languages. First, we extend the notion of <i>lexical triggers</i>, which have been used monolingually for language model adaptation, to the cross-lingual problem, permitting the construction of sharper language models for a target-language document by drawing statistics from related documents in a resource-rich language. Next, we show that <i>cross-lingual latent semantic analysis</i> is similarly capable of extracting useful statistics for language modeling. Neither technique requires explicit translation capabilities between the two languages! We demonstrate significant reductions in both perplexity and word error rate on a Mandarin speech recognition task by using these techniques.

REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

	1	Michael W. Berry , Susan T. Dumais , Gavin W. O'Brien, Using linear algebra for intelligent information retrieval, SIAM Review, v.37 n.4, p.573-595, Dec. 1995 [doi>10.1137/1037127]
	2	Peter F. Brown , Vincent J. Della Pietra , Stephen A. Della Pietra , Robert L. Mercer, The mathematics of statistical machine translation: parameter estimation, Computational Linguistics, v.19 n.2, June 1993
	3	Byrne, W. et al. 2000. Towards language independent acoustic modeling. In Proceedings of the ICASSP, vol. 2. 1029--1032.
	4	Coccaro, N. and Jurafsky, D. 1998. Towards better integration of semantic predictors in statistical language modeling. In Proceedings of the ICSLP, Sydney, Australia, vol. 6. 2403--2406.
	5	Doermann, D. et al. 2002. Lexicon acquisition from bilingual dictionaries. In Proceedings of the SPIE Photonic West Article Imaging Conference, San Jose, CA. 37--48.
	6	Dumais, S. et al. 1997. Automatic cross-language retrieval using latent semantic indexing. In AAAI Spring Symposium on Cross-Language Text and Speech Retrieval.
	7	Fung, P. et al. 2000. Pronunciation modeling of Mandarin casual speech. 2000 Johns Hopkins Summer Workshop. Available at http://www.clsp.jhu.edu/ws2000/groups/mcs.
	8	Iyer, R. and Ostendorf, M. 1999. Modeling long-distance dependence in language: topic-mixtures vs dynamic cache models. IEEE Trans. Speech Audio Process. 7, 30--39.
	9	Khudanpur, S. and Kim, W. 2002. Using cross-language cues for story-specific language modeling. In Proceedings of the ICSLP, Denver, CO, vol. 1. 513--516.
	10	Woosung Kim , Sanjeev Khudanpur, Cross-lingual lexical triggers in statistical language modeling, Proceedings of the 2003 conference on Empirical methods in natural language processing, p.17-24, July 11, 2003 [doi>10.3115/1119355.1119358]
	11	Kirchhoff, K. et al. 2002. Novel speech recognition models for Arabic. 2002 Johns Hopkins Summer Workshop. Available at http://www.clsp.jhu.edu/ws2002/groups/arabic.
	12	LDC. 2000. Hong Kong news parallel text corpus. Available through the Linguistic Data Consortium. http://www.ldc.upenn.edu/Catalog/LDC2000T46.html.
	13	Franz Josef Och , Hermann Ney, Improved statistical alignment models, Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, p.440-447, October 03-06, 2000, Hong Kong [doi>10.3115/1075218.1075274]
	14	Pallett, D., Fisher, W., and Fiscus, J. 1990. Tools for the analysis of benchmark speech recognition tests. In Proceedings of the ICASSP, Alburquerque, NM, vol. 1. 97--100.
	15	Rosenfeld, R. 1996. A maximum entropy approach to adaptive statistical language modeling. Comput. Speech Lang. 10, 187--228.
	16	Schultz, T. and Waibel, A. 1998. Language independent and language adaptive large vocabulary speech recognition. In Proceedings of the ICSLP, Sydney, Australia, vol. 5. 1819--1822.
	17	Tillmann, C. and Ney, H. 1997. Word trigger and the EM algorithm. In Proceedings of the Workshop Computational Natural Language Learning (CoNLL 97), Madrid, Spain. 117--124.
	18	David Yarowsky , Grace Ngai , Richard Wicentowski, Inducing multilingual text analysis tools via robust projection across aligned corpora, Proceedings of the first international conference on Human language technology research, p.1-8, March 18-21, 2001, San Diego [doi>10.3115/1072133.1072187]