Abstract
Part-of-Speech Tagging is a problem in Natural Language Processing (NLP) which consists of grammatically labeling textual elements. To accomplish this task, there are models either rule-based or driven by machine learning algorithms. Though semi-supervised strategies have been proposed recently, this work employs a fully supervised learning technique. This technique is the Averaged Perceptron, already applied to the POS Tagging task in English, and used for the Brazilian Portuguese language in this work. An accuracy superior to 97% was achieved, as it was also shown that it is possible to speed up the convergence time of the algorithm more than two times using parallel training strategies.
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
- 1.
This implies in an important property from the Structured Perceptron, which is being able to observe all the elements of the structure, and no only the local ones. This property is emphasized by Collins [3] when the so called Global Linear Models are defined.
References
Aluisio S, Pelizzoni J, Marchi AR, de Oliveira L, Manenti R, Marquiafável V (2003) An account of the challenge of tagging a reference corpus for brazilian portuguese. In: Proceedings of computational processing of the Portuguese language. Springer, pp 110–117
Collins M (2002) Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms. In: Proceedings of the ACL-02 conference on empirical methods in natural language processing, vol 10. Association for computational linguistics, pp 1–8
Collins M (2013) Natural language processing. https://www.coursera.org/course/nlangp. Accessed 05 2013
Dos Santos CN, MIlidiú RL, Rentera RP () Portuguese part-of-speech tagging using entropy guided transformation learning. Avaiable in Computational processing of the portuguese language. Springer, pp 143–152
Fonseca ER, Rosa JLG (2013) Mac-morpho revisited: towards robust part-of-speech tagging. In: Proceedings of the 9th Brazilian symposium in information and human language technology, pp 98–107
Mcdonald R, Hall K, Mann G (2010) Distributed training strategies for the structured perceptron. In: Proceedings of human language technologies: the 2010 annual conference of the north American chapter of the association for computational linguistics. Association for computational linguistics, pp 456–464
Ratnaparkhi A (1996) A maximum entropy model for part-of-speech tagging. In: Proceedings of the conference on empirical methods in natural language processing, vol 1. pp 133-142
Rojas R (1996) Neural networks: a systematic introduction. Springer science & business media
ACL WIKI. Pos tagging (state of the art). http://wiki.aclweb.org/. Last modified in 26 Nov 2014
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Miasato, V.A., Gonçalves, B., Costa, B.R., De Carvalho Silva, J.E. (2017). Distributed Averaged Perceptron for Brazilian Portuguese Part-of-Speech Tagging. In: Paradisi, A., Godoy Souza Mello, A., Lira Figueiredo, F., Carvalho Figueiredo, R. (eds) Cognitive Technologies. Telecommunications and Information Technology. Springer, Cham. https://doi.org/10.1007/978-3-319-53753-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-53753-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-53752-8
Online ISBN: 978-3-319-53753-5
eBook Packages: EngineeringEngineering (R0)