mlsanityData to 7 Oct 2026

From Hyperbolic Geometry Back to Word Embeddings

arXiv 2204.12481 ↗First posted 26 Apr 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 31 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

13 of 31 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2018Deep contextualized word representationscited by 2,285
  6. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  7. 2018Poincar'e GloVe: Hyperbolic Word Embeddingscited by 155
  8. 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 96
  9. 2019Analogies Explained: Towards Understanding Word Embeddingscited by 63
  10. 2018Towards Understanding Linear Word Analogiescited by 57
  11. 2018What the Vec? Towards Probabilistically Grounded Embeddingscited by 8
  12. 2015The Mechanism of Additive Compositioncited by 2
1 more
  1. 2019Context Vectors are Reflections of Word Vectors in Half the Dimensionscited by 2

Built on by

Not cited yet.