G. Boleda and S. Pado and J. Utt. Regular polysemy: A distributional model. Proceedings of *SEM 2012. Montreal, Canada.
Many types of polysemy are not word specific, but are instances of general sense alternations such as Animal-Food. Despite their pervasiveness, regular alternations have been mostly ignored in empirical computational semantics. This paper presents (a) a general framework which grounds sense alternations in corpus data, generalizes them above individual words, and allows the prediction of alternations for new words; and (b) a concrete unsupervised implementation of the framework, the Centroid Attribute Model. We evaluate this model against a set of 2,400 ambiguous words and demonstrate that it outperforms two baselines.
The dataset is available from my data page.
@InProceedings{boleda12:regular, author = {Gemma Boleda and Sebastian Pad\'o and Jason Utt}, title = {Regular polysemy: A distributional model}, booktitle = {Proceedings of *SEM 2012}, year = 2012, address = {Montreal, Canada}}