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

Fix tagger when some tags aren't in Morphology

This commit is contained in:
Matthew Honnibal 2017-11-01 19:27:49 +01:00
parent e85e31cfbd
commit 190522efd3
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/pipeline.pyx
View File

@ -394,8 +394,7 @@ class Tagger(Pipe):
def get_loss(self, docs, golds, scores): def get_loss(self, docs, golds, scores):
scores = self.model.ops.flatten(scores) scores = self.model.ops.flatten(scores)
tag_index = {tag: i tag_index = {tag: i for i, tag in enumerate(self.labels)}
for i, tag in enumerate(self.vocab.morphology.tag_names)}
cdef int idx = 0 cdef int idx = 0
correct = numpy.zeros((scores.shape[0],), dtype='i') correct = numpy.zeros((scores.shape[0],), dtype='i')
guesses = scores.argmax(axis=1) guesses = scores.argmax(axis=1)
@ -426,9 +425,12 @@ class Tagger(Pipe):
new_tag_map[tag] = {POS: X} new_tag_map[tag] = {POS: X}
cdef Vocab vocab = self.vocab cdef Vocab vocab = self.vocab
if new_tag_map: if new_tag_map:
new_tag_map.update(orig_tag_map)
vocab.morphology = Morphology(vocab.strings, new_tag_map, vocab.morphology = Morphology(vocab.strings, new_tag_map,
vocab.morphology.lemmatizer, vocab.morphology.lemmatizer,
exc=vocab.morphology.exc) exc=vocab.morphology.exc)
for tag in vocab.morphology.tag_names:
self.add_label(tag)
if self.model is True: if self.model is True:
self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1] self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
self.model = self.Model(self.vocab.morphology.n_tags, **self.cfg) self.model = self.Model(self.vocab.morphology.n_tags, **self.cfg)