New paper "Riemannian Optimization for Skip-Gram Negative Sampling"
April 26, 2017
Ivan Oseledets finilized new publication "Riemannian Optimization for Skip-Gram Negative Sampling". In this work the new approach, based on low rank tensor approximations, is proposed for optimization of word embedding models learning. The work is performed under MegaGrant support.
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.