From Hyperbolic Geometry Back to Word Embeddings
Zhenisbek Assylbekov, Sultan Nurmukhamedov, Arsen Sheverdin, Thomas Mach
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.- Anthology ID:
- 2022.repl4nlp-1.5
- Volume:
- Proceedings of the 7th Workshop on Representation Learning for NLP
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- RepL4NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 39–45
- Language:
- URL:
- https://aclanthology.org/2022.repl4nlp-1.5
- DOI:
- 10.18653/v1/2022.repl4nlp-1.5
- Cite (ACL):
- Zhenisbek Assylbekov, Sultan Nurmukhamedov, Arsen Sheverdin, and Thomas Mach. 2022. From Hyperbolic Geometry Back to Word Embeddings. In Proceedings of the 7th Workshop on Representation Learning for NLP, pages 39–45, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- From Hyperbolic Geometry Back to Word Embeddings (Assylbekov et al., RepL4NLP 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.repl4nlp-1.5.pdf
- Code
- soltustik/rhg