Abstract
We propose a supervised approach to word sense disambiguation based on neural networks combined with evolutionary algorithms. Large tagged datasets for every sense of a polysemous word are considered, and used to evolve an optimized neural network that correctly disambiguates the sense of the given word considering the context in which it occurs.
A new distributed scheme based on a lexicographic encoding to represent the context in which a particular word occurs is proposed.
The viability of the approach has been demonstrated through experiments carried out on a representative set of polysemous words.
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
Azzini, A., Dragoni, M., da Costa Pereira, C., Tettamanzi, A.: Evolving neural networks for word sense disambiguation. In: Proc. of HIS 2008, Barcelona, Spain, September 10-12, pp. 332–337 (2008)
Azzini, A., Tettamanzi, A.: Evolving neural networks for static single-position automated trading. Journal of Artificial Evolution and Applications 2008(Article ID 184286), 1–17 (2008)
Cottrell, G.: A Connectionist Approach to Word Sense Disambiguation. Pitman, London (1989)
Escudero, G., Màrquez, L., Rigau, G.: An empirical study of the domain dependence of supervised word sense disambiguation systems. In: Proc. of the Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora, Morristown, NJ, USA, pp. 172–180. ACL (2000)
Escudero, D.M., Màrquez, G.L., Rigau, G.: Supervised Corpus-Based Methods for WSD, pp. 167–207. Springer Netherlands, Heidelberg (2006)
Hinton, G., McClelland, J., Rumelhart, D.: Distributed representations. In: Parellel Distributed Processing: explorations in the microstructure of cognition. MIT Press, Cambridge (1986)
Hovy, E., Mitchell, M., Palmer, M., Ramshaw, L., Weischedel, R.: Ontonotes: The 90% solution. In: Proc. of the Human Language Technology Conf., New York, pp. 57–60 (2006)
Navigli, R.: Word sense disambiguation: A survey. ACM Comput. Surv. 41(2), 1–69 (2009)
Ng, H.: Exemplar-based word sense disambiguation: some recent improvements. In: Proc. of EMNLP 1997, pp. 208–213 (1997)
Schapire, R., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)
Tratz, S., Sanfilippo, A., Gregory, M., Chappell, A., Posse, C., Whitney, P.: Pnnl: A supervised maximum entropy approach to word sense disambiguation. In: Proc. of Int. Workshop on Semantic Evaluations SemEval 2007, Prague, June 2007, pp. 264–267. Association of Computational Linguistics (2007)
Vapnik, V.: Statistical Learning Theory. John Wiley & Sons, Chichester (1998)
Yao, X., Liu, Y.: A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks 8(3), 694–713 (1997)
Yarowsky, D.: Hierarchical decision lists for word sense disambiguation. Computational Humanities 34(2), 179–186 (2000)
Zhou, X., Han, H.: Survey of word sense disambiguation approaches. In: Proc. of the Int. Artificial Intelligence Research Society Conference, Clearwater Beach, Florida, USA, pp. 307–313. AAAI Press, Menlo Park (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Azzini, A., da Costa Pereira, C., Dragoni, M., Tettamanzi, A.G.B. (2009). A Lexicographic Encoding for Word Sense Disambiguation with Evolutionary Neural Networks. In: Serra, R., Cucchiara, R. (eds) AI*IA 2009: Emergent Perspectives in Artificial Intelligence. AI*IA 2009. Lecture Notes in Computer Science(), vol 5883. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10291-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-10291-2_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10290-5
Online ISBN: 978-3-642-10291-2
eBook Packages: Computer ScienceComputer Science (R0)