Abstract
Multiword Expressions (MWEs) display some kind of linguistic and statistical markedness that may influence the effectiveness of techniques that automatically identify them in texts. While parsing-based techniques for MWE identification are considered to be better at handling long-distance dependencies, passivization and internal modification, statistics-based techniques use association measures to detect statistical markedness regardless of syntactic form. In this paper we compare these two approaches focusing on nominal compounds in Portuguese. We compare the accuracy of each method and propose that combining the strengths of both for increased accuracy.
Keywords
- Multiword Expressions
- Basic Statistical Techniques
- Statistical Association Measures
- Long-distance Dependencies
- Automatic Validation
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Buying options
Notes
- 1.
Parsing increased the number of tokens from 49 to 67 million words as contractions like those involving preposition and determiner are expanded to de + o by the parser (e.g. do (of the)).
- 2.
Among the 100 top candidates from each process, some were already validated in the automatic validation step. The manual validation was applied only to those MWE candidates that were not prevalidated.
References
Bick, E.: The parsing system Palavras: Automatic grammatical analysis of Portuguese in a constraint grammar framework. Aarhus Universitetsforlag (2000)
Calzolari, N., Fillmore, C.J., Grishman, R., Ide, N., Lenci, A., MacLeod, C., Zampolli, A.: Towards best practice for multiword expressions in computational lexicons. In: Proceedings of the Third International Conference on Language Resources and Evaluation (LREC-2002), Las Palmas, Canary Islands, Spain. European Language Resources Association (ELRA), May 2002
Evert, S., Krenn, B.: Using small random samples for the manual evaluation of statistical association measures. Comput. Speech Lang. 19(4), 450–466 (2005)
Koehn, P.: Europarl: a parallel corpus for statistical machine translation. In: Conference Proceedings: The Tenth Machine Translation Summit, pp. 79–86. AAMT, Phuket (2005)
Navigli, R., Ponzetto, S.P.: BabelNet: building a very large multilingual semantic network. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 216–225. Association for Computational Linguistics (2010)
Oliveira, H.G., Gomes, P.: Onto.pt: automatic construction of a lexical ontology for portuguese. In: Stairs 2010: Proceedings of the Fifth Starting AI Researchers’ Symposium, vol. 222, p. 199. IOS Press (2010)
Pecina, P.: Lexical association measures and collocation extraction. Lang. Resour. Eval. 44(1–2), 137–158 (2010)
Ramisch, C., Schreiner, P., Idiart, M., Villavicencio, A.: An evaluation of methods for the extraction of multiword expressions. In: Proceedings of the LREC Workshop Towards a Shared Task for Multiword Expressions (MWE 2008), pp. 50–53 (2008)
Ramisch, C., Villavicencio, A., Boitet, C.: Multiword expressions in the wild?: the mwetoolkit comes in handy. In: Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations, pp. 57–60. Association for Computational Linguistics (2010)
Seretan, V.: Syntax-Based Collocation Extraction, Text, Speech and Language Technology, vol. 44, 1st edn, p. 212. Dordrecht, Netherlands (2011)
Wehrli, E., Nerima, L.: The fips multilingual parser. In: Gala, E., Rapp, R., Bel-Enguix, G. (eds.) Language Production, Cognition, and the Lexicon. Text, Speech and Language Technology, vol. 48, pp. 473–490. Springer, Switzerland (2015)
Wehrli, E., Seretan, V., Nerima, L.: Sentence analysis and collocation identification. In: 23rd International Conference on Computational Linguistics, COLING (2010)
Acknowledgments
This research was partially developed in the context of the project Text Simplification of Complex Expressions, sponsored by Samsung Eletrônica da Amazônia Ltda., in the terms of the Brazilian law n. 8.248/91. This work was also partly supported by CNPq (482520/2012-4, 312114/2015-0) and FAPERGS.
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
Zilio, L., Wilkens, R., Möllmann, L., Wehrli, E., Cordeiro, S., Villavicencio, A. (2016). Joining Forces for Multiword Expression Identification. In: Silva, J., Ribeiro, R., Quaresma, P., Adami, A., Branco, A. (eds) Computational Processing of the Portuguese Language. PROPOR 2016. Lecture Notes in Computer Science(), vol 9727. Springer, Cham. https://doi.org/10.1007/978-3-319-41552-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-41552-9_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41551-2
Online ISBN: 978-3-319-41552-9
eBook Packages: Computer ScienceComputer Science (R0)