Factorization of Latent Variables in Distributional Semantic Models

Arvid Österlund, David Ödling, Magnus Sahlgren

Abstract

This paper discusses the use of factorization techniques in distributional semantic models. We focus on a method for redistributing the weight of latent variables, which has previously been shown to improve the performance of distributional semantic models. However, this result has not been replicated and remains poorly understood. We refine the method, and provide additional theoretical justification, as well as empirical results that demonstrate the viability of the proposed approach.
BibTeX
@inproceedings{osterlund2015factorization,
  author = {Arvid Österlund and David Ödling and Magnus Sahlgren},
  title = {{Factorization of Latent Variables in Distributional Semantic Models}},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1024},
}
Figure