Papers › Squashed Shifted PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces

Squashed Shifted PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces

27 Feb 2020arXiv:2002.12005archive 2025-07-28

Zhenisbek Assylbekov, Alibi Jangeldin

We show that removing sigmoid transformation in the skip-gram with negative sampling (SGNS) objective does not harm the quality of word vectors significantly and at the same time is related to factorizing a squashed shifted PMI matrix which, in turn, can be treated as a connection probabilities matrix of a random graph. Empirically, such graph is a complex network, i.e. it has strong clustering and scale-free degree distribution, and is tightly connected with hyperbolic spaces. In short, we show the connection between static word embeddings and hyperbolic spaces through the squashed shifted PMI matrix using analytical and empirical methods.

PaperPDFCode

Code

zh3nis/BPMI officialmentioned in papermentioned on GitHubpytorch report
zh3nis/SGNS officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections