From Hyperbolic Geometry Back to Word Embeddings
2022-04-26RepL4NLP (ACL) 2022Code Available0· sign in to hype
Sultan Nurmukhamedov, Thomas Mach, Arsen Sheverdin, Zhenisbek Assylbekov
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/soltustik/rhgOfficialIn paperpytorch★ 1
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.