400k English-language GloVe word embeddings (300 dimensions)

A matrix of 400 thousand word vectors (rows) of 300 dimensions (columns). Embeddings were trained on the 2014 Wikipedia and Gigaword 5 corpora (total of 6 billion tokens).

data("vecs_glove300_wiki_gigaword")

Format

A matrix of 400 thousand rows and 300 columns

Source

https://nlp.stanford.edu/projects/glove/

References

Pennington, Jeffrey, Richard Socher, and Christopher Manning. (2014). "Glove: Global Vectors for Word Representation." Pp. 1532--43 in Proceedings of the 2014 conference on empirical methods in natural language processing