From Hyperbolic Geometry Back to Word Embeddings

04/26/2022

∙

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.

READ FULL TEXT

From Hyperbolic Geometry Back to Word Embeddings

Hyperbolic Centroid Calculations for Text Classification

Binarized PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces

Poincaré GloVe: Hyperbolic Word Embeddings

A Theory of Hyperbolic Prototype Learning

Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions

From Hyperbolic Geometry Back to Word Embeddings

Related Research

Hyperbolic Centroid Calculations for Text Classification

Binarized PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces

Poincaré GloVe: Hyperbolic Word Embeddings

A Theory of Hyperbolic Prototype Learning

Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions