Is Cosine-Similarity of Embeddings Really About Similarity?

• word2vec

  3 1,490 0.0 C

  Automatically exported from code.google.com/p/word2vec

The original paper included source, and that has their test data and results -- it gets ~77% accuracy on about 20k example word analogies (with 99.7% coverage), and 78% accuracy with phrases with 77% coverage. You can see the test set here:

https://github.com/tmikolov/word2vec/blob/master/questions-w...

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

Suggest a related project