From Hyperbolic Geometry Back to Word Embeddings
Computation and Language
2022-04-27 v1
Abstract
We choose random points in the hyperbolic disc and claim that these points are already word representations. However, it is yet to be uncovered which point corresponds to which word of the human language of interest. This correspondence can be approximately established using a pointwise mutual information between words and recent alignment techniques.
Cite
@article{arxiv.2204.12481,
title = {From Hyperbolic Geometry Back to Word Embeddings},
author = {Sultan Nurmukhamedov and Thomas Mach and Arsen Sheverdin and Zhenisbek Assylbekov},
journal= {arXiv preprint arXiv:2204.12481},
year = {2022}
}