Encoding Prior Knowledge with Eigenword Embeddings
Computation and Language
2016-07-28 v3
Abstract
Canonical correlation analysis (CCA) is a method for reducing the dimension of data represented using two views. It has been previously used to derive word embeddings, where one view indicates a word, and the other view indicates its context. We describe a way to incorporate prior knowledge into CCA, give a theoretical justification for it, and test it by deriving word embeddings and evaluating them on a myriad of datasets.
Keywords
Cite
@article{arxiv.1509.01007,
title = {Encoding Prior Knowledge with Eigenword Embeddings},
author = {Dominique Osborne and Shashi Narayan and Shay B. Cohen},
journal= {arXiv preprint arXiv:1509.01007},
year = {2016}
}
Comments
in Transactions of the Association of Computational Linguistics (TACL), 2016