English

Outperforming Word2Vec on Analogy Tasks with Random Projections

Computation and Language 2015-02-18 v2 Machine Learning

Abstract

We present a distributed vector representation based on a simplification of the BEAGLE system, designed in the context of the Sigma cognitive architecture. Our method does not require gradient-based training of neural networks, matrix decompositions as with LSA, or convolutions as with BEAGLE. All that is involved is a sum of random vectors and their pointwise products. Despite the simplicity of this technique, it gives state-of-the-art results on analogy problems, in most cases better than Word2Vec. To explain this success, we interpret it as a dimension reduction via random projection.

Keywords

Cite

@article{arxiv.1412.6616,
  title  = {Outperforming Word2Vec on Analogy Tasks with Random Projections},
  author = {Abram Demski and Volkan Ustun and Paul Rosenbloom and Cody Kommers},
  journal= {arXiv preprint arXiv:1412.6616},
  year   = {2015}
}

Comments

This paper has been withdrawn due to problems pointed out in review

R2 v1 2026-06-22T07:39:08.587Z