[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.5555/1687878.1687890dlproceedingsArticle/Chapter ViewAbstractPublication PagesaclConference Proceedingsconference-collections
research-article
Free access

Unsupervised multilingual grammar induction

Published: 02 August 2009 Publication History

Abstract

We investigate the task of unsupervised constituency parsing from bilingual parallel corpora. Our goal is to use bilingual cues to learn improved parsing models for each language and to evaluate these models on held-out monolingual test data. We formulate a generative Bayesian model which seeks to explain the observed parallel data through a combination of bilingual and monolingual parameters. To this end, we adapt a formalism known as unordered tree alignment to our probabilistic setting. Using this formalism, our model loosely binds parallel trees while allowing language-specific syntactic structure. We perform inference under this model using Markov Chain Monte Carlo and dynamic programming. Applying this model to three parallel corpora (Korean-English, Urdu-English, and Chinese-English) we find substantial performance gains over the CCM model, a strong monolingual baseline. On average, across a variety of testing scenarios, our model achieves an 8.8 absolute gain in F-measure.

References

[1]
Ann Bies, Martha Palmer, Justin Mott, and Colin Warner. 2007. English Chinese translation treebank v 1.0. LDC2007T02.
[2]
Phil Blunsom, Trevor Cohn, and Miles Osborne. 2008. Bayesian synchronous grammar induction. In Proceedings of NIPS.
[3]
David Burkett and Dan Klein. 2008. Two languages are better than one (for syntactic parsing). In Proceedings of EMNLP, pages 877--886.
[4]
Eugene Charniak and Glen Carroll. 1992. Two experiments on learning probabilistic dependency grammars from corpora. In Proceedings of the AAAI Workshop on Statistically-Based NLP Techniques, pages 1--13.
[5]
David Chiang. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of the ACL, pages 263--270.
[6]
Shay B. Cohen and Noah A. Smith. 2009. Shared logistic normal distributions for soft parameter tying in unsupervised grammar induction. In Proceedings of the NAACL/HLT.
[7]
Jason Eisner. 2003. Learning non-isomorphic tree mappings for machine translation. In The Companion Volume to the Proceedings of the ACL, pages 205--208.
[8]
Andrew Gelman, John B. Carlin, Hal S. Stern, and Donald B. Rubin. 2004. Bayesian data analysis. Chapman and Hall/CRC.
[9]
Dmitriy Genzel. 2005. Inducing a multilingual dictionary from a parallel multitext in related languages. In Proceedings of EMNLP/HLT, pages 875--882.
[10]
C. Han, N. R. Han, E. S. Ko, H. Yi, and M. Palmer. 2002. Penn Korean Treebank: Development and evaluation. In Proc. Pacific Asian Conf. Language and Comp.
[11]
W. K. Hastings. 1970. Monte carlo sampling methods using Markov chains and their applications. Biometrika, 57:97--109.
[12]
R. Hwa, P. Resnik, A. Weinberg, C. Cabezas, and O. Kolak. 2005. Bootstrapping parsers via syntactic projection across parallel texts. Journal of Natural Language Engineering, 11(3):311--325.
[13]
T. Jiang, L. Wang, and K. Zhang. 1995. Alignment of trees -- an alternative to tree edit. Theoretical Computer Science, 143(1):137--148.
[14]
M. Johnson, T. Griffiths, and S. Goldwater. 2007. Bayesian inference for PCFGs via Markov chain Monte Carlo. In Proceedings of the NAACL/HLT, pages 139--146.
[15]
Dan Klein and Christopher D. Manning. 2002. A generative constituent-context model for improved grammar induction. In Proceedings of the ACL, pages 128--135.
[16]
D. Klein. 2005. The Unsupervised Learning of Natural Language Structure. Ph.D. thesis, Stanford University.
[17]
Jonas Kuhn. 2004. Experiments in parallel-text based grammar induction. In Proceedings of the ACL, pages 470--477.
[18]
I. Dan Melamed. 2003. Multitext grammars and synchronous parsers. In Proceedings of the NAACL/HLT, pages 79--86.
[19]
Franz Josef Och and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1):19--51.
[20]
Yoav Seginer. 2007. Fast unsupervised incremental parsing. In Proceedings of the ACL, pages 384--391.
[21]
David A. Smith and Noah A. Smith. 2004. Bilingual parsing with factored estimation: Using English to parse Korean. In Proceeding of EMNLP, pages 49--56.
[22]
Benjamin Snyder and Regina Barzilay. 2008. Unsupervised multilingual learning for morphological segmentation. In Proceedings of the ACL/HLT, pages 737--745.
[23]
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, and Regina Barzilay. 2008. Unsupervised multilingual learning for POS tagging. In Proceedings of EMNLP, pages 1041--1050.
[24]
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, and Regina Barzilay. 2009. Adding more languages improves unsupervised multilingual part-of-speech tagging: A Bayesian non-parametric approach. In Proceedings of the NAACL/HLT.
[25]
Andreas Stolcke and Stephen M. Omohundro. 1994. Inducing probabilistic grammars by Bayesian model merging. In Proceedings of ICGI, pages 106--118.
[26]
Dekai Wu and Hongsing Wong. 1998. Machine translation with a stochastic grammatical channel. In Proceedings of the ACL/COLING, pages 1408--1415.
[27]
Dekai Wu. 1997. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational Linguistics, 23(3):377--403.
[28]
Chenhai Xi and Rebecca Hwa. 2005. A backoff model for bootstrapping resources for non-english languages. In Proceedings of EMNLP, pages 851--858.
[29]
Hao Zhang and Daniel Gildea. 2005. Stochastic lexicalized inversion transduction grammar for alignment. In Proceedings of the ACL, pages 475--482.

Cited By

View all
  • (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
  • (2012)Crosslingual induction of semantic rolesProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390615(647-656)Online publication date: 8-Jul-2012
  • (2012)Selective sharing for multilingual dependency parsingProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390613(629-637)Online publication date: 8-Jul-2012
  • Show More Cited By

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings
ACL '09: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
August 2009
572 pages
ISBN:9781932432459
  • General Chair:
  • Keh-Yih Su

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 02 August 2009

Qualifiers

  • Research-article

Acceptance Rates

Overall Acceptance Rate 85 of 443 submissions, 19%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)55
  • Downloads (Last 6 weeks)3
Reflects downloads up to 14 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (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
  • (2012)Crosslingual induction of semantic rolesProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390615(647-656)Online publication date: 8-Jul-2012
  • (2012)Selective sharing for multilingual dependency parsingProceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 110.5555/2390524.2390613(629-637)Online publication date: 8-Jul-2012
  • (2011)Relaxed cross-lingual projection of constituent syntaxProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/2145432.2145558(1192-1201)Online publication date: 27-Jul-2011
  • (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
  • (2011)Inducing sentence structure from parallel corpora for reorderingProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/2145432.2145455(193-203)Online publication date: 27-Jul-2011
  • (2011)Unsupervised structure prediction with non-parallel multilingual guidanceProceedings of the Conference on Empirical Methods in Natural Language Processing10.5555/2145432.2145439(50-61)Online publication date: 27-Jul-2011
  • (2011)Using large monolingual and bilingual corpora to improve coordination disambiguationProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 110.5555/2002472.2002639(1346-1355)Online publication date: 19-Jun-2011
  • (2011)Unsupervised part-of-speech tagging with bilingual graph-based projectionsProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 110.5555/2002472.2002549(600-609)Online publication date: 19-Jun-2011
  • (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
  • 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

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media