research-article

Free access

Adding more languages improves unsupervised multilingual part-of-speech tagging: a Bayesian non-parametric approach

Authors:

Benjamin Snyder,

Tahira Naseem,

Jacob Eisenstein,

Regina BarzilayAuthors Info & Claims

NAACL '09: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Pages 83 - 91

Published: 31 May 2009 Publication History

PDF eReader

Abstract

We investigate the problem of unsupervised part-of-speech tagging when raw parallel data is available in a large number of languages. Patterns of ambiguity vary greatly across languages and therefore even unannotated multilingual data can serve as a learning signal. We propose a non-parametric Bayesian model that connects related tagging decisions across languages through the use of multilingual latent variables. Our experiments show that performance improves steadily as the number of languages increases.

References

[1]

C. E. Antoniak. 1974. Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems. The Annals of Statistics, 2:1152--1174, November.

Crossref

Google Scholar

[2]

Trevor Cohn and Mirella Lapata. 2007. Machine translation by triangulation: Making effective use of multiparallel corpora. In Proceedings of ACL.

Google Scholar

[3]

T. Erjavec. 2004. MULTEXT-East version 3: Multilingual morphosyntactic specifications, lexicons and corpora. In Fourth International Conference on Language Resources and Evaluation, LREC, volume 4, pages 1535--1538.

Google Scholar

[4]

Anna Feldman, Jirka Hana, and Chris Brew. 2006. A cross-language approach to rapid creation of new morpho-syntactically annotated resources. In Proceedings of LREC, pages 549--554.

Google Scholar

[5]

Dmitriy Genzel. 2005. Inducing a multilingual dictionary from a parallel multitext in related languages. In Proceedings of the HLT/EMNLP, pages 875--882.

Digital Library

Google Scholar

[6]

Sharon Goldwater and Thomas L. Griffiths. 2007. A fully Bayesian approach to unsupervised part-of-speech tagging. In Proceedings of the ACL, pages 744--751.

Google Scholar

[7]

W. K. Hastings. 1970. Monte Carlo sampling methods using Markov chains and their applications. Biometrika, 57:97--109.

Crossref

Google Scholar

[8]

Franz Josef Och and Hermann Ney. 2001. Statistical multi-source translation. In MT Summit 2001, pages 253--258.

Google Scholar

[9]

Franz Josef Och and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1):19--51.

Digital Library

Google Scholar

[10]

J. Sethuraman. 1994. A constructive definition of Dirichlet priors. Statistica Sinica, 4:639--650.

Google Scholar

[11]

Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, and Regina Barzilay. 2008. Unsupervised multilingual learning for POS tagging. In Proceedings of the EMNLP, pages 1041--1050.

Digital Library

Google Scholar

[12]

Masao Utiyama and Hitoshi Isahara. 2006. A comparison of pivot methods for phrase-based statistical machine translation. In Proceedings of NAACL/HLT, pages 484--491.

Google Scholar

[13]

David Yarowsky and Grace Ngai. 2001. Inducing multilingual POS taggers and NP bracketers via robust projection across aligned corpora. In Proceedings of the NAACL, pages 1--8.

Digital Library

Google Scholar

Cited By

View all

Kim YSnyder BTsujii JHenderson JPasca M(2012)Universal grapheme-to-phoneme prediction over Latin alphabetsProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning10.5555/2390948.2390990(332-343)Online publication date: 12-Jul-2012
https://dl.acm.org/doi/10.5555/2390948.2390990
Täckström OCohn TBlunsom PGraca J(2012)Nudging the envelope of direct transfer methods for multilingual named entity recognitionProceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure10.5555/2390426.2390435(55-63)Online publication date: 7-Jun-2012
https://dl.acm.org/doi/10.5555/2390426.2390435
Bhargava AKondrak GChu-Carroll J(2012)Leveraging supplemental representations for sequential transductionProceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies10.5555/2382029.2382085(396-406)Online publication date: 3-Jun-2012
https://dl.acm.org/doi/10.5555/2382029.2382085
Show More Cited By

Index Terms

Adding more languages improves unsupervised multilingual part-of-speech tagging: a Bayesian non-parametric approach
1. Applied computing
  1. Arts and humanities
    1. Language translation
2. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Speech recognition

Recommendations

Unsupervised Joint PoS Tagging and Stemming for Agglutinative Languages

The number of possible word forms is theoretically infinite in agglutinative languages. This brings up the out-of-vocabulary (OOV) issue for part-of-speech (PoS) tagging in agglutinative languages. Since inflectional morphology does not change the PoS ...
Unsupervised Part-of-Speech Tagging in the Large

Syntactic preprocessing is a step that is widely used in NLP applications. Traditionally, rule-based or statistical Part-of-Speech (POS) taggers are employed that either need considerable rule development times or a sufficient amount of manually labeled ...
Feature-rich part-of-speech tagging for morphologically complex languages: application to Bulgarian
EACL '12: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

We present experiments with part-of-speech tagging for Bulgarian, a Slavic language with rich inflectional and derivational morphology. Unlike most previous work, which has used a small number of grammatical categories, we work with 680 morpho-syntactic ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

NAACL '09: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics

May 2009

716 pages

ISBN:9781932432411

General Chair:
Mari Ostendorf
University of Washington
,
Program Chairs:
Michael Collins
Massachusetts Institute of Technology
,
Shri Narayanan
University of Southern California
,
Douglas W. Oard
Microsoft Research

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 31 May 2009

Qualifiers

Research-article

Acceptance Rates

Overall Acceptance Rate 21 of 29 submissions, 72%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
286
Total Downloads

Downloads (Last 12 months)37
Downloads (Last 6 weeks)4

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Kim YSnyder BTsujii JHenderson JPasca M(2012)Universal grapheme-to-phoneme prediction over Latin alphabetsProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning10.5555/2390948.2390990(332-343)Online publication date: 12-Jul-2012
https://dl.acm.org/doi/10.5555/2390948.2390990
Täckström OCohn TBlunsom PGraca J(2012)Nudging the envelope of direct transfer methods for multilingual named entity recognitionProceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure10.5555/2390426.2390435(55-63)Online publication date: 7-Jun-2012
https://dl.acm.org/doi/10.5555/2390426.2390435
Bhargava AKondrak GChu-Carroll J(2012)Leveraging supplemental representations for sequential transductionProceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies10.5555/2382029.2382085(396-406)Online publication date: 3-Jun-2012
https://dl.acm.org/doi/10.5555/2382029.2382085
Kim YGraça JSnyder BMerlo PBarzilay RJohnson M(2011)Universal morphological analysis using structured nearest neighbor predictionProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/2145432.2145470(322-332)Online publication date: 27-Jul-2011
https://dl.acm.org/doi/10.5555/2145432.2145470
McDonald RPetrov SHall KMerlo PBarzilay RJohnson M(2011)Multi-source transfer of delexicalized dependency parsersProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/2145432.2145440(62-72)Online publication date: 27-Jul-2011
https://dl.acm.org/doi/10.5555/2145432.2145440
Snyder BBarzilay R(2010)Climbing the tower of babelProceedings of the 27th International Conference on International Conference on Machine Learning10.5555/3104322.3104328(29-36)Online publication date: 21-Jun-2010
https://dl.acm.org/doi/10.5555/3104322.3104328
Reichart RFattal RRappoport ALapata M(2010)Improved unsupervised POS induction using intrinsic clustering quality and a Zipfian constraintProceedings of the Fourteenth Conference on Computational Natural Language Learning10.5555/1870568.1870577(57-66)Online publication date: 15-Jul-2010
https://dl.acm.org/doi/10.5555/1870568.1870577
Samardžić TMerlo PXia FLewis WLevin L(2010)Cross-lingual variation of light verb constructionsProceedings of the 2010 Workshop on NLP and Linguistics: Finding the Common Ground10.5555/1870166.1870174(52-60)Online publication date: 16-Jul-2010
https://dl.acm.org/doi/10.5555/1870166.1870174
Berg-Kirkpatrick TKlein DHajič J(2010)Phylogenetic grammar inductionProceedings of the 48th Annual Meeting of the Association for Computational Linguistics10.5555/1858681.1858812(1288-1297)Online publication date: 11-Jul-2010
https://dl.acm.org/doi/10.5555/1858681.1858812
Ganchev KGraça JGillenwater JTaskar B(2010)Posterior Regularization for Structured Latent Variable ModelsThe Journal of Machine Learning Research10.5555/1756006.185991811(2001-2049)Online publication date: 1-Aug-2010
https://dl.acm.org/doi/10.5555/1756006.1859918
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

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

Abstract

References

Cited By

Index Terms

Recommendations

Unsupervised Joint PoS Tagging and Stemming for Agglutinative Languages

Unsupervised Part-of-Speech Tagging in the Large

Feature-rich part-of-speech tagging for morphologically complex languages: application to Bulgarian

Comments

Information

Published In

Publisher

Publication History

Qualifiers

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

PDF

eReader

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations