explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix handling of unseen labels in tagger

Browse Source
This commit is contained in:
Matthew Honnibal 2018-06-25 22:24:54 +02:00
parent 3aabf621a3
commit 5b56aad4c2
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/pipeline.pyx
View File

@ -501,6 +501,7 @@ class Tagger(Pipe):
cdef int idx = 0
correct = numpy.zeros((scores.shape[0],), dtype='i')
guesses = scores.argmax(axis=1)
known_labels = numpy.ones((scores.shape[0],), dtype='f')
for gold in golds:
for tag in gold.tags:
if tag is None:
@ -508,10 +509,12 @@ class Tagger(Pipe):
elif tag in tag_index:
correct[idx] = tag_index[tag]
else:
correct[idx] = len(tag_index)+1
correct[idx] = 0
known_labels[idx] = 0.
idx += 1
correct = self.model.ops.xp.array(correct, dtype='i')
d_scores = scores - to_categorical(correct, nb_classes=scores.shape[1])
d_scores *= known_labels
loss = (d_scores**2).sum()
d_scores = self.model.ops.unflatten(d_scores, [len(d) for d in docs])
return float(loss), d_scores