Abstract
There is a growing interest in unsupervised grammar induction, which does not require syntactic annotations, but provides less accurate results than the supervised approach. Aiming at improving the accuracy of the unsupervised approach, we have resorted to additional information, which can be obtained more easily. Shallow parsing or chunking identifies the sentence constituents (noun phrases, verb phrases, etc.), but without specifying their internal structure. There exist highly accurate systems to perform this task, and thus this information is available even for languages for which large syntactically annotated corpora are lacking. In this work we have investigated how the results of a pattern-based unsupervised grammar induction system improve as data on new kind of phrases are added, leading to a significant improvement in performance. We have analyzed the results for three different languages. We have also shown that the system is able to significantly improve the results of the unsupervised system using the chunks provided by automatic chunkers.
Supported by projects Holopedia (TIN2010-21128-C02) and MA2VICMR (S2009/TIC-1542).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Araujo, L., Serrano, J.I.: Highly accurate error-driven method for noun phrase detection. Pattern Recognition Letters 29(4), 547–557 (2008)
Bod, R.: Unsupervised parsing with u-dop. In: CoNLL-X 2006: Proceedings of the Tenth Conference on Computational Natural Language Learning, pp. 85–92. Association for Computational Linguistics, Morristown (2006)
Haghighi, A., Klein, D.: Prototype-driven grammar induction. In: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pp. 881–888. Association for Computational Linguistics (2006)
Huang, L.: Forest reranking: Discriminative parsing with non-local features. In: Proc. of ACL (2008)
Klein, D., Manning, C.D.: Natural language grammar induction with a generative constituent-context model. Pattern Recognition 38(9), 1407–1419 (2005)
Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of english: The penn treebank. Computational Linguistics 19(2), 313–330 (1994), citeseer.ist.psu.edu/marcus93building.html
Moreno, A., Grishman, R., Lopez, S., Sanchez, F., Sekine, S.: A treebank of spanish and its application to parsing. In: LREC 2000: Proceedings of the International Conference on Language Resources & Evaluation, pp. 107–111. European Language Resources Association, ELRA (2000)
Petrov, S.: Products of random latent variable grammars. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, HLT 2010, pp. 19–27 (2010)
Petrov, S., Klein, D.: Improved inference for unlexicalized parsing. In: HLT-NAACL, pp. 404–411 (2007)
Sang, E.F.T.K.: Memory-Based Shallow Parsing. ArXiv Computer Science e-prints (April 2002)
Santamaría, J., Araujo, L.: Identifying patterns for unsupervised grammar induction. In: Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pp. 38–45. Association for Computational Linguistics, Uppsala (2010), http://www.aclweb.org/anthology/W10-2905
Seginer, Y.: Fast unsupervised incremental parsing. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 384–391 (2007)
Sha, F., Pereira, F.: Shallow parsing with conditional random fields. In: Proceedings of HLT-NAACL 2003, pp. 213–220 (2003)
Shen, H., Sarkar, A.: Voting Between Multiple Data Representations for Text Chunking. In: Kégl, B., Lee, H.-H. (eds.) AI 2005. LNCS (LNAI), vol. 3501, pp. 389–400. Springer, Heidelberg (2005)
Skut, W., Krenn, B., Brants, T., Uszkoreit, H.: An annotation scheme for free word order languages. In: Proceedings of the Fifth Conference on Applied Natural Language Processing, ANLC 1997, pp. 88–95. Association for Computational Linguistics (1997)
Zhang, H., Zhang, M., Tan, C.L., Li, H.: K-best combination of syntactic parsers. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, vol. 3, pp. 1552–1560 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Santamaría, J., Araujo, L. (2013). Semi-supervised Constituent Grammar Induction Based on Text Chunking Information. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2013. Lecture Notes in Computer Science, vol 7816. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37247-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-37247-6_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37246-9
Online ISBN: 978-3-642-37247-6
eBook Packages: Computer ScienceComputer Science (R0)