From Hyperbolic Geometry Back to Word Embeddings

dc.contributor.author	Assylbekov Zhenisbek
dc.contributor.author	Nurmukhamedov Sultan
dc.contributor.author	Sheverdin Arsen
dc.contributor.author	Mach Thomas
dc.date.accessioned	2025-08-27T04:56:29Z
dc.date.available	2025-08-27T04:56:29Z
dc.date.issued	2022-01-01
dc.description.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.	en
dc.identifier.citation	Assylbekov Zhenisbek; Nurmukhamedov Sultan; Sheverdin Arsen; Mach Thomas. (2022). From Hyperbolic Geometry Back to Word Embeddings. Proceedings of the 7th Workshop on Representation Learning for NLP. https://doi.org/10.18653/v1/2022.repl4nlp-1.5	en
dc.identifier.doi	10.18653/v1/2022.repl4nlp-1.5
dc.identifier.uri	https://doi.org/10.18653/v1/2022.repl4nlp-1.5
dc.identifier.uri	https://nur.nu.edu.kz/handle/123456789/10455
dc.language.iso	en
dc.publisher	Association for Computational Linguistics
dc.source	(2022)	en
dc.title	From Hyperbolic Geometry Back to Word Embeddings	en
dc.type	conference-paper	en

Files

Now showing 1 - 1 of 1