Applicative structure in vector space models

Abstract

We introduce a new 50-dimensional embedding obtained by spectral clustering of a graph describing the conceptual structure of the lexicon. We use the embedding directly to investigate sets of antonymic pairs, and indirectly to argue that function application in CVSMs requires not just vectors but two transformations (corresponding to subject and object) as well.

Extracted Key Phrases

6 Figures and Tables

Cite this paper

@inproceedings{Makrai2013ApplicativeSI, title={Applicative structure in vector space models}, author={M{\'a}rton Makrai and D{\'a}vid M{\'a}rk Nemeskey and Andr{\'a}s Kornai}, year={2013} }