By-decade word2vec (SGNS) embeddings trained on Google N-Grams chi-sim-all (Simplified Chinese, 1950-1990s).
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/