Automatic identification of non-compositional multi-word expressions using latent semantic analysis (2006)
| Venue: | In Proceedings of the ACL/COLING-06 Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties |
| Citations: | 41 - 1 self |
BibTeX
@INPROCEEDINGS{Katz06automaticidentification,
author = {Graham Katz},
title = {Automatic identification of non-compositional multi-word expressions using latent semantic analysis},
booktitle = {In Proceedings of the ACL/COLING-06 Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties},
year = {2006},
pages = {12--19}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Making use of latent semantic analysis, we explore the hypothesis that local linguistic context can serve to identify multi-word expressions that have noncompositional meanings. We propose that vector-similarity between distribution vectors associated with an MWE as a whole and those associated with its constitutent parts can serve as a good measure of the degree to which the MWE is compositional. We present experiments that show that low (cosine) similarity does, in fact, correlate with non-compositionality. 1
Citations
No citations identified.
