CLApr 26, 2022
From Hyperbolic Geometry Back to Word Embeddings
arXiv:2204.12481v1638 citationsh-index: 15
Originality Synthesis-oriented
AI Analysis
This is an incremental approach for natural language processing, focusing on word representation alignment.
The paper tackles the problem of mapping random hyperbolic points to word embeddings by using pointwise mutual information and alignment techniques, but it does not provide concrete results or numbers.
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.