6

So I'd like to use some of this training data in spaCy when I use the similarity() method.

I'd also like to maybe use the pre-trained vectors also on this page.

But the spaCy docs seem lacking here, does anyone know how to do this?

Tom Carrick
  • 6,349
  • 13
  • 54
  • 78

1 Answers1

3

Unfortunately the docs for this still aren't linked on the site! We're reworking the docs. But, does this answer your question: https://spacy.io/tutorials/load-new-word-vectors

syllogism_
  • 4,127
  • 29
  • 22
  • Mostly yes. Do you know if the google news vectors I linked are compatible? – Tom Carrick Feb 26 '16 at 14:51
  • Also, are there any resources on training data into vectors? – Tom Carrick Feb 26 '16 at 14:52
  • The Google news vectors you linked should work fine. I think you missed the link though! The Gensim docs have advice about training word vectors, as does the user group for word2vec. We're recommending you consider pre-processing the text with the spaCy tools before learning the vector. See the 'sense2vec' blog post for details on why this is helpful. – syllogism_ Feb 26 '16 at 15:04
  • There's a link in the link in my question :P But thanks, very helpful. – Tom Carrick Feb 26 '16 at 16:11
  • 3
    hi @syllogism_ that link is dead! – leon yin Jun 15 '17 at 17:31