Abstract
In this chapter, we describe the approach which makes use of the information of bilexical dependencies from auto-parsed data in order to improve parsing accuracy. First, all the sentences in the unlabeled data are parsed by a baseline parser. Subsequently, information on short dependency relations is extracted from the parsed data, because the accuracies for short dependencies are relatively higher than those for others. Finally, we train another parser by using the extracted information as features.
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
Notes
- 1.
Precision represents the percentage of predicted arcs of length d that are correct, and recall measures the percentage of gold-standard arcs of length d that are correctly predicted.F 1 = 2 × precision × recall∕(precision + recall).
- 2.
More detailed information can be found at http://www.cis.upenn.edu/~chinese/
- 3.
More detailed information can be found at http://www.icl.pku.edu
- 4.
An unknown word is the word that is not included in training data.
References
Brants, T. (2000). TnT–a statistical part-of-speech tagger. In Proceedings of ANLP, Seattle (pp. 224–231).
Chen, W., Kawahara, D., Uchimoto, K., Zhang, Y., & Isahara, H. (2008). Dependency parsing with short dependency relations in unlabeled data. In Proceedings of IJCNLP 2008, Hyderabad.
McDonald, R., & Nivre, J. (2007). Characterizing the errors of data-driven dependency parsing models. In Proceedings of EMNLP-CoNLL, Prague (pp. 122–131).
Nivre, J. (2003). An efficient algorithm for projective dependency parsing. In Proceedings of IWPT 2003, Nancy (pp. 149–160).
Nivre, J., & Kubler, S. (2006). Dependency parsing: Tutorial at Coling-ACL 2006. In CoLING-ACL, Sydney.
Reichart, R., & Rappoport, A. (2007). Self-training for enhancement and domain adaptation of statistical parsers trained on small datasets. In: Proceedings of ACL, Prague.
Sagae, K., & Tsujii, J. (2007). Dependency parsing and domain adaptation with LR models and parser ensembles. In Proceedings of the CoNLL shared task session of EMNLP-CoNLL 2007, Prague (pp. 1044–1050).
van Noord, G. (2007). Using self-trained bilexical preferences to improve disambiguation accuracy. In Proceedings of IWPT-07, Prague.
Wang, M., Sagae, K., & Mitamura, T. (2006). A fast, accurate deterministic parser for Chinese. In Proceedings of Coling-ACL 2006, Sydney.
Wang, Q. I., Lin, D., & Schuurmans, D. (2007). Simple training of dependency parsers via structured boosting. In Proceedings of IJCAI 2007, Hyderabad.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer Science+Business Media Singapore
About this chapter
Cite this chapter
Chen, W., Zhang, M. (2015). Training with Bilexical Dependencies. In: Semi-Supervised Dependency Parsing. Springer, Singapore. https://doi.org/10.1007/978-981-287-552-5_6
Download citation
DOI: https://doi.org/10.1007/978-981-287-552-5_6
Publisher Name: Springer, Singapore
Print ISBN: 978-981-287-551-8
Online ISBN: 978-981-287-552-5
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)