Thanks a lot for your open-source resources! I found the model that obtained the best performance in hypernymy evaluation 50x2D Poincare GloVe, h(x) = x^2 , init trick (190k) is missing in the released pre-trained vectors. Is it convenient for you to make the trained vectors for this configuration public? Thanks a lot!
Description
TODO: change commented example
Steps/Code/Corpus to Reproduce
Expected Results
Actual Results
Versions
Hi Alex,
Thanks a lot for your open-source resources! I found the model that obtained the best performance in hypernymy evaluation
50x2D Poincare GloVe, h(x) = x^2 , init trick (190k)
is missing in the released pre-trained vectors. Is it convenient for you to make the trained vectors for this configuration public? Thanks a lot!