By-decade word2vec (SGNS) embeddings trained on Corpus of Historical American English (Genre-Balanced American English, 1830s-2000s).

rds files are R numeric matrices with tokens as rownames.

References:

William L. Hamilton, Jure Leskovec, and Dan Jurafsky. ACL 2016. Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change. https://nlp.stanford.edu/projects/histwords/

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.