Flair: ELMO pubmed model

[nstfk]

Elmo now has a new model trained on the PubMed corpus, check ( https://allennlp.org/elmo under contributed model)
Is this supported in Flair the same way the others (original, medium, small and Portuguese) are supported?
And is there a possibility to embed sentences using my own pre-trained ELMO/BERT models?
Thank you!

[stefan-it]

@nstfk The portugese model is currently supported.

If you want to use the new PubMed model, I'll open a PR to support it :)

[nstfk]

Wow, that was quick
And yes please, I am trying to evaluate and compare Flair/ELMO/BERT embedding on medical downstream tasks..

[stefan-it]

PR is created :) Once it is merged, you can use the PubMed model with:

from flair.embeddings import ELMoEmbeddings

embeddings = ELMoEmbeddings('pubmed')

This will download weights and options for the ELMo model.

[cpmss521]

hai..when i use:
embedding = ELMoEmbeddings('pubmed'),
embed = embedding.embed(sentence)
for token in sentence:
print(token)
print(token.get_embedding())
print(token.get_embedding().shape)
and i get torch.Size([3072]),why is 3072?? @stefan-it ,thanks

[stefan-it]

@cpmss521 By default, ELMo outputs three 1024d vectors for each token. In flair we currently concatenate all three layers :) Btw. here's an issue that discusses that further #647.

[cpmss521]

thanks !