Conceptual Spaces: The Geometry of Thought
Conceptual Spaces: The Geometry of Thought
Automatic word sense discrimination
Computational Linguistics - Special issue on word sense disambiguation
Co-occurrence vectors from corpora vs. distance vectors from dictionaries
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Geometry and Meaning
Orthogonal negation in vector spaces for modelling word-meanings and document retrieval
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Hi-index | 0.00 |
This paper examines what kind of similarity between words can be represented by what kind of word vectors in the vector space model. Through two experiments, three methods for constructing word vectors, i.e., LSA-based, cooccurrence-based and dictionary-based methods, were compared in terms of the ability to represent two kinds of similarity, i.e., taxonomic similarity and associative similarity. The result of the comparison was that the dictionary-based word vectors better reflect taxonomic similarity, while the LSA-based and the cooccurrence-based word vectors better reflect associative similarity.