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. The viability of the approach has been demonstrated through experiments carried out on a representative set of polysemous words.
Evolving neural networks for word sense disambiguation / A. Azzini, C. da Costa Pereira, M. Dragoni, A.G.B. Tettamanzi - In: Eighth international conference on hybrid intelligent systems : Barcelona, Spain, september 10-12, 2008 : proceedings / [a cura di] F. Xhafa ... [et al.]. - Los Alamitos : Institute of electrical and electronics engineers, 2008. - ISBN 9780769533261. - pp. 332-337 (( Intervento presentato al 8. convegno International Conference on Hybrid Intelligent Systems (HIS) tenutosi a Barcelona, Spain nel 2008 [10.1109/HIS.2008.88].
Evolving neural networks for word sense disambiguation
A. AzziniPrimo
;C. da Costa PereiraSecondo
;M. DragoniPenultimo
;A.G.B. TettamanziUltimo
2008
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. The viability of the approach has been demonstrated through experiments carried out on a representative set of polysemous words.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
