Skip to contents

SGNS embeddings trained on the British National Corpus. Each term is also tagged with part-of-speech, e.g. "hyperventilation_NOUN"

Format

A matrix of 163,473 rows and 300 columns

Source

http://vectors.nlpl.eu/repository/

References

Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. "Efficient Estimation of Word Representations in Vector Space."" In Proceedings of Workshop at ICLR