Katrin Erk and Sebastian Pado: Towards a Computational Model of Gradience in Word Sense. Proceedings of IWCS-7, Tilburg, The Netherlands.
In the construction of lexicons or word sense inventories, researchers have usually strived to dene a set of disjoint senses for a word; however, there is increasing evidence that this is impossible in the general case. In this programmatic paper, we support this point with sense overlap data from manual sense annotation. We then sketch the road towards a fundamentally graded representation of word sense that is still amenable to integration into a theory of sentence semantics.
@InProceedings{erk07:_towar_comput_model_gradien_word_sense,
author = {Katrin Erk and Sebastian Pado},
title = {Towards a Computational Model of
Gradience in Word Sense},
booktitle = {Proceedings of IWCS-7},
year = 2007,
address = {Tilburg, The Netherlands}
}