Abstract
In this paper, we present a method of improving dependency parsing accuracy by combining parsers using error rates. We use four parsers: MSTParser, MaltParser, TurboParser and MateParser, and the data of the analytical layer of the Prague Dependency Treebank. We parse data with each of the parsers and calculate error rates for several parameters such as POS of dependent tokens. These error rates are then used to determine weights of edges in an oriented graph created by merging all the parses of a sentence provided by the parsers. We find the maximum spanning tree in this graph (a dependency tree without cycles), and achieve a 1.3 % UAS/1.1 % LAS improvement compared to the best parser in our experiment.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Bohnet, B., Nivre, J.: A transition-based system for joint part-of-speech tagging and labeled non-projective dependency parsing. In: Proceedings of EMNLP 2012 (2012)
Chen, D., Manning, C.D.: A fast and accurate dependency parser using neural networks. In: Proceedings of EMNLP 2014 (2014)
Green, N.D.: Improvements to syntax-based machine translation using ensemble dependency parsers (thesis). Faculty of Mathematics and Physics, Charles University, Prague (2013)
Hajič, J.: Complex corpus annotation: the Prague dependency treebank. In: Šimková, M. (ed.) Insight into the Slovak and Czech Corpus Linguistics, pp. 54–73. Veda, Bratislava (2006)
Martins, A.F.T., Almeida, M.B., Smith, N.A.: Turning on the turbo: fast third-order non-projective turbo parsers. In: Proceedings of ACL 2013 (2013)
McDonald, R., Pereira, F., Ribarov, K., Hajic, J.: Non-projective dependency parsing using spanning tree algorithms. In: Proceedings of EMNLP 2005 (2005)
Nivre, J., Hall, J., Nilsson, J.: MaltParser: a data-driven parser-generator for dependency parsing. In: Proceedings of LREC 2006 (2006)
Straka, M., Hajič, J., Straková, J., Hajič jr., J.: Parsing universal dependency treebanks using neural networks and search-based Oracle. In: Proceedings of TLT 2015 (2015)
Acknowledgments
This research was supported by Czech Ministry of Education, Youth and Sports through the Czech National Corpus project (LM2015044). A part of the computational resources used in our experiments were provided by the CESNET project (LM2015042). Both projects are part of the programme Large Research, Development, and Innovations Infrastructures.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Jelínek, T. (2016). Combining Dependency Parsers Using Error Rates. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2016. Lecture Notes in Computer Science(), vol 9924. Springer, Cham. https://doi.org/10.1007/978-3-319-45510-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-45510-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45509-9
Online ISBN: 978-3-319-45510-5
eBook Packages: Computer ScienceComputer Science (R0)