search

oborchers / Fast_Sentence_Embeddings

Compute Sentence Embeddings Fast!
GNU General Public License v3.0
619 stars 83 forks source link

Paranmt Model #48

Closed grantmwilliams closed 2 years ago

grantmwilliams commented 2 years ago

Is there any information on getting the paranmt model or setting it up? The benchmarks show it as a great model to use with FSE and I was hoping to try it out, but I haven't been able to find it anywhere (just training data). I was just curious if there was somewhere we could access this model/keyed vectors.

oborchers commented 2 years ago

Hi @grantmwilliams!

Back then I downloaded the paranmt model from here I think: https://www.cs.cmu.edu/~jwieting/ https://aclanthology.org/P18-1042.pdf

But I've found a zip on my computer. It looks incredibly small, so I uploaded it (barely 200mb, 72k words x 300d)

https://drive.google.com/file/d/1PMekZGfVsIdSN9q7qgw13M4mPQ_oiGTJ/view?usp=sharing

It needs to be manually converted to a BaseKeyedVector object though

oborchers commented 2 years ago

@grantmwilliams I'm working on 0.2.0. It will provide downloadable vectors, including these ones. Stay tuned.

oborchers commented 2 years ago

@grantmwilliams the model is now accessible using:

from fse import Vectors, Average

vecs = Vectors.from_pretrained("paranmt-300")
model = Average(vecs)