Riemannian Optimization for Skip-Gram Negative Sampling

Alexander Fonarev, Oleksii Grinchuk, Gleb Gusev, Pavel Serdyukov, Ivan Oseledets


Abstract
Skip-Gram Negative Sampling (SGNS) word embedding model, well known by its implementation in “word2vec” software, is usually optimized by stochastic gradient descent. However, the optimization of SGNS objective can be viewed as a problem of searching for a good matrix with the low-rank constraint. The most standard way to solve this type of problems is to apply Riemannian optimization framework to optimize the SGNS objective over the manifold of required low-rank matrices. In this paper, we propose an algorithm that optimizes SGNS objective using Riemannian optimization and demonstrates its superiority over popular competitors, such as the original method to train SGNS and SVD over SPPMI matrix.
Anthology ID:
P17-1185
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2028–2036
Language:
URL:
https://aclanthology.org/P17-1185
DOI:
10.18653/v1/P17-1185
Bibkey:
Cite (ACL):
Alexander Fonarev, Oleksii Grinchuk, Gleb Gusev, Pavel Serdyukov, and Ivan Oseledets. 2017. Riemannian Optimization for Skip-Gram Negative Sampling. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2028–2036, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Riemannian Optimization for Skip-Gram Negative Sampling (Fonarev et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1185.pdf
Poster:
 P17-1185.Poster.pdf
Code
 AlexGrinch/ro_sgns