Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Don't use tags when calculating token vectors

This commit is contained in:
Matthew Honnibal 2017-05-08 07:52:24 -05:00
parent 7a33f1e2b7
commit 56073a11ef
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/_ml.py
View File

@ -185,13 +185,12 @@ def build_tok2vec(lang, width, depth=2, embed_size=1000):
prefix = get_col(cols.index(PREFIX)) >> HashEmbed(width, embed_size) prefix = get_col(cols.index(PREFIX)) >> HashEmbed(width, embed_size)
suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size) suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size)
shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size) shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size)
tag = get_col(cols.index(TAG)) >> HashEmbed(width, embed_size)
tok2vec = ( tok2vec = (
doc2feats(cols) doc2feats(cols)
>> with_flatten( >> with_flatten(
#(static | prefix | suffix | shape) #(static | prefix | suffix | shape)
(lower | prefix | suffix | shape | tag) (lower | prefix | suffix | shape)
>> Maxout(width, width*5) >> Maxout(width, width*4)
>> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3))) >> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3)))
>> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3))) >> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3)))
>> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3))) >> Residual((ExtractWindow(nW=1) >> Maxout(width, width*3)))