Year: 2022
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Nurmukhamedov, Sultan, Mach, Thomas, Sheverdin, Arsen, Assylbekov, Zhenisbek
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Nazarbayev University
Award: G1726468424
OpenAlex ID: W4225003333