AutoNER icon indicating copy to clipboard operation
AutoNER copied to clipboard

Could not get the bio_embedding.txt file

Open www-Ye opened this issue 2 years ago • 3 comments

Hello, the link to bio_embedding.txt does not open, where can I get this file?

www-Ye avatar Sep 20 '22 07:09 www-Ye

Same problem here. Seems the server is down. Could anyone help to share the embedding file? Thanks.

fuzihaofzh avatar Oct 04 '22 13:10 fuzihaofzh

Same problem here. Seems the server is down. Could anyone help to share the embedding file? Thanks.

I used the website http://bio.nlplab.org/ mentioned in footnote 7 of the original paper to download the original .bin format word2vec file and then used gensim to convert it to .txt format, perhaps to get the same embedding

www-Ye avatar Oct 04 '22 16:10 www-Ye

Thanks @www-Ye , it helps a lot.

I don't know whether I am correct, but the following code can get the program running. No guarantee of getting the same results.

! wget http://evexdb.org/pmresources/vec-space-models/wikipedia-pubmed-and-PMC-w2v.bin
from gensim.models.keyedvectors import KeyedVectors
model = KeyedVectors.load_word2vec_format(
       "./wikipedia-pubmed-and-PMC-w2v.bin", binary=True
 )
model.save_word2vec_format("bio_embedding.txt", binary=False)

fuzihaofzh avatar Oct 07 '22 15:10 fuzihaofzh