Proceedings of the 18th Nordic Conference of Computational Linguistics NODALIDA
The following work describes a method to automatically classify the sense selection of the complex type Location/Organization ¿which depends on regular polysemy¿ using shallow features, as well as a way to increase the volume of sense-selection gold standards by using monosemous data as filler. The classifier results show that grammatical features are the most relevant cues for the identification of sense selection in this instance of regular polysemy.
Martínez Alonso, Héctor; Sandford Pedersen, Bolette; Bel Rafecas, Núria. Identification of sense selection in regular polysemy using shallow features. In: Standford Pedersen, Bolette; Nespore, Gunta; Skadia, Inguna. Proceedings of the 18th Nordic Conference of Computational Linguistics NODALIDA. 1 ed. Latvia: NEALT; 2011. p. 18-25.