Deconstructing word embedding algorithms
Abstract
Word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Uncontextualized word embeddings are used in many NLP tasks today, especially in resource-limited settings where high memory capacity and GPUs are not available. Given the historical success of word embeddings in NLP, we propose a retrospective on some of the most well-known word embedding algorithms. In this work, we deconstruct Word2vec, GloVe, and others, into a common form, unveiling some of the common conditions that seem to be required for making performant word embeddings. We believe that the theoretical findings in this paper can provide a basis for more informed development of future models.
Cite
@article{arxiv.2011.07013,
title = {Deconstructing word embedding algorithms},
author = {Kian Kenyon-Dean and Edward Newell and Jackie Chi Kit Cheung},
journal= {arXiv preprint arXiv:2011.07013},
year = {2020}
}
Comments
EMNLP 2020, 6 pages. arXiv admin note: substantial text overlap with arXiv:1911.13280