research-article

Free access

Mixture-model adaptation for SMT

Authors:

Roland KuhnAuthors Info & Claims

StatMT '07: Proceedings of the Second Workshop on Statistical Machine Translation

Pages 128 - 135

Published: 23 June 2007 Publication History

Abstract

We describe a mixture-model approach to adapting a Statistical Machine Translation System for new domains, using weights that depend on text distances to mixture components. We investigate a number of variants on this approach, including cross-domain versus dynamic adaptation; linear versus loglinear mixtures; language and translation model adaptation; different methods of assigning weights; and granularity of the source unit being adapted to. The best methods achieve gains of approximately one BLEU percentage point over a state-of-the art non-adapted baseline system.

References

[1]

Peter F. Brown, Stephen A. Della Pietra, Vincent Della J. Pietra, and Robert L. Mercer. 1993. The mathematics of Machine Translation: Parameter estimation. Computational Linguistics, 19(2):263--312, June.

Digital Library

[2]

W. Byrne, S. Khudanpur, W. Kim, S. Kumar, P. Pecina, P. Virga, P. Xu, and D. Yarowsky. 2003. The JHU 2003 Chinese-English Machine Translation System. In MT Summit IX, New Orleans, September.

[3]

S. Deerwester, S. T. Dumais, G. W. Furnas, T. K. Landauer, and R. Harshman. 1990. Indexing by latent semantic analysis. JASIS, 41(6):391--407.

[4]

Radu Florian and David Yarowsky. 1999. Dynamic nonlocal language modeling via hierarchical topic-based adaptation. In ACL 1999, pages 167--174, College Park, Maryland, June.

Digital Library

[5]

George Foster, Roland Kuhn, and Howard Johnson. 2006. Phrasetable smoothing for statistical machine translation. In EMNLP 2006, Sydney, Australia.

Digital Library

[6]

Trevor Hastie, Robert Tibshirani, and Jerome Friedman. 2001. The Elements of Statistical Learning. Springer.

[7]

Almut Silja Hildebrand, Matthias Eck, Stephan Vogel, and Alex Waibel. 1995. Adaptation of the translation model for statistical machine translation based on information retrieval. In EAMT 1995, Budapest, May.

[8]

R. Iyer and M. Ostendorf. 1999. Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models. In IEEE Trans on Speech and Language Processing, 1999.

[9]

Frederick Jelinek. 1997. Statistical Methods for Speech Recognition. MIT Press.

Digital Library

[10]

Reinhard Kneser and Volker Steinbiss. 1993. On the dynamic adaptation of stochastic language models. In ICASSP 1993, pages 586--589, Minneapolis, Minnesota. IEEE.

[11]

Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In NAACL 2003, pages 127--133.

Digital Library

[12]

Roland Kuhn and Renato De Mori. 1990. A cache-based natural language model for speech recognition. IEEE Trans on PAMI, 12(6):570--583, June.

Digital Library

[13]

Percy Liang, Alexandre Bouchard-Côté, Dan Klein, and Ben Taskar. 2006. An end-to-end discriminative approach to machine translation. In ACL 2006

Digital Library

[14]

Franz Josef Och. 2003. Minimum error rate training for statistical machine translation. In ACL 2003, Sapporo, July.

Digital Library

[15]

Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2001. BLEU: A method for automatic evaluation of Machine Translation. Technical Report RC22176, IBM, September.

Digital Library

[16]

William H. Press, Saul A. Teukolsky, William T. Vetterling, and Brian P. Flannery. 2002. Numerical Recipes in C++. Cambridge University Press, Cambridge, UK.

[17]

Christoph Tillmann and Tong Zhang. 2006. A discriminative global training algorithm for statistical MT. In ACL 2006.

Digital Library

[18]

Nicola Ueffing. 2006. Self-training for machine translation. In NIPS 2006 Workshop on MLIA, Whistler, B.C., December.

[19]

Richard Zens and Hermann Ney. 2004. Improvements in phrase-based statistical machine translation. In HLT/NAACL 2004, Boston, May.

[20]

R. Zhang, H. Yamamoto, M. Paul, H. Okuma, K. Yasuda, Y. Lepage, E. Denoual, D. Mochihashi, A. Finch, and E. Sumita. 2006. The NiCT-ATR statistical machine translation system for the IWSLT 2006 evaluation. In IWSLT 2006.

[21]

Bing Zhao, Matthias Eck, and Stephan Vogel. 2004. Language model adaptation for statistical machine translation with structured query models. In COLING 2004, Geneva, August.

Digital Library

Cited By

Abdul-Rauf SSchwenk HLambert PNawaz M(2016)Empirical use of information retrieval to build synthetic data for SMT domain adaptationIEEE/ACM Transactions on Audio, Speech and Language Processing10.1109/TASLP.2016.251731824:4(745-754)Online publication date: 1-Apr-2016
https://dl.acm.org/doi/10.1109/TASLP.2016.2517318
Biçici EYuret D(2015)Optimizing instance selection for statistical machine translation with feature decay algorithmsIEEE/ACM Transactions on Audio, Speech and Language Processing10.1109/TASLP.2014.238188223:2(339-350)Online publication date: 1-Feb-2015
https://dl.acm.org/doi/10.1109/TASLP.2014.2381882
Pecina PToral APapavassiliou VProkopidis PTamchyna AWay AGenabith J(2015)Domain adaptation of statistical machine translation with domain-focused web crawlingLanguage Resources and Evaluation10.1007/s10579-014-9282-349:1(147-193)Online publication date: 1-Mar-2015
https://dl.acm.org/doi/10.1007/s10579-014-9282-3
Show More Cited By

Recommendations

Syntactically Lexicalized Phrase-Based SMT

Until quite recently, extending phrase-based statistical machine translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent successful enrichments of PBSMT with hierarchical structure either employ ...
Flattened Syntactical Phrase-Based Translation Model for SMT
ICCPOL '09: Proceedings of the 22nd International Conference on Computer Processing of Oriental Languages. Language Technology for the Knowledge-based Economy

This paper proposed a flattened syntactical phrase-based translation model for Statistical Machine Translation (SMT) learned from bilingual parallel parsed texts. The flattened syntactical phrases are sets of ordered leaf nodes with their father nodes ...
Domain Adaptation for SMT Using Sentence Weight
Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data
Abstract
We describe a sentence-level domain adaptation translation system, which trained with the sentence-weight model. Our system can take advantage of the domain information in each sentence rather than in the corpus. It is a fine-grained method for ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

StatMT '07: Proceedings of the Second Workshop on Statistical Machine Translation

June 2007

281 pages

Program Chairs:
Chris Callison-Burch
Johns Hopkins University
,
Philipp Koehn
University of Edinburgh
,
Christof Monz
Queen Mary, University of London
,
Cameron Shaw Fordyce
Center for the Evaluation of Language and Communication Technologies

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 23 June 2007

Qualifiers

Research-article

Acceptance Rates

StatMT '07 Paper Acceptance Rate 12 of 38 submissions, 32%;

Overall Acceptance Rate 24 of 59 submissions, 41%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

41
Total Citations
View Citations
495
Total Downloads

Downloads (Last 12 months)78
Downloads (Last 6 weeks)22

Reflects downloads up to 16 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Abdul-Rauf SSchwenk HLambert PNawaz M(2016)Empirical use of information retrieval to build synthetic data for SMT domain adaptationIEEE/ACM Transactions on Audio, Speech and Language Processing10.1109/TASLP.2016.251731824:4(745-754)Online publication date: 1-Apr-2016
https://dl.acm.org/doi/10.1109/TASLP.2016.2517318
Biçici EYuret D(2015)Optimizing instance selection for statistical machine translation with feature decay algorithmsIEEE/ACM Transactions on Audio, Speech and Language Processing10.1109/TASLP.2014.238188223:2(339-350)Online publication date: 1-Feb-2015
https://dl.acm.org/doi/10.1109/TASLP.2014.2381882
Pecina PToral APapavassiliou VProkopidis PTamchyna AWay AGenabith J(2015)Domain adaptation of statistical machine translation with domain-focused web crawlingLanguage Resources and Evaluation10.1007/s10579-014-9282-349:1(147-193)Online publication date: 1-Mar-2015
https://dl.acm.org/doi/10.1007/s10579-014-9282-3
Bertoldi NCettolo MFederico MBuck C(2012)Evaluating the learning curve of domain adaptive statistical machine translation systemsProceedings of the Seventh Workshop on Statistical Machine Translation10.5555/2393015.2393076(433-441)Online publication date: 7-Jun-2012
https://dl.acm.org/doi/10.5555/2393015.2393076
Haddow BKoehn P(2012)Analysing the effect of out-of-domain data on SMT systemsProceedings of the Seventh Workshop on Statistical Machine Translation10.5555/2393015.2393075(422-432)Online publication date: 7-Jun-2012
https://dl.acm.org/doi/10.5555/2393015.2393075
Formiga LHenríquez Q. CHernández AMariño JMonte EFonollosa J(2012)The TALP-UPC phrase-based translation systems for WMT12Proceedings of the Seventh Workshop on Statistical Machine Translation10.5555/2393015.2393053(275-282)Online publication date: 7-Jun-2012
https://dl.acm.org/doi/10.5555/2393015.2393053
Lu SWei WFu XXu BTsujii JHenderson JPasca M(2012)Translation model based cross-lingual language model adaptationProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning10.5555/2390948.2391008(512-522)Online publication date: 12-Jul-2012
https://dl.acm.org/doi/10.5555/2390948.2391008
Razmara MFoster GSankaran BSarkar ALi HLin COsborne M(2012)Mixing multiple translation models in statistical machine translationProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390652(940-949)Online publication date: 8-Jul-2012
https://dl.acm.org/doi/10.5555/2390524.2390652
Xiao XXiong DZhang MLiu QLin SLi HLin COsborne M(2012)A topic similarity model for hierarchical phrase-based translationProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390630(750-758)Online publication date: 8-Jul-2012
https://dl.acm.org/doi/10.5555/2390524.2390630
Su JWu HWang HChen YShi XDong HLiu QLi HLin COsborne M(2012)Translation model adaptation for statistical machine translation with monolingual topic informationProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390589(459-468)Online publication date: 8-Jul-2012
https://dl.acm.org/doi/10.5555/2390524.2390589
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

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 Publication

Figures

Tables

Media

View Table of Conten