explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add dep to supertag.

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-08 07:50:01 -05:00
parent 6782eedf9b
commit 7a33f1e2b7
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
bin/parser/train_ud.py
View File

@ -55,7 +55,9 @@ def read_conllx(loc, n=0):
id_ = int(id_) - 1 id_ = int(id_) - 1
head = (int(head) - 1) if head != '0' else id_ head = (int(head) - 1) if head != '0' else id_
dep = 'ROOT' if dep == 'root' else dep #'unlabelled' dep = 'ROOT' if dep == 'root' else dep #'unlabelled'
tokens.append((id_, word, pos+'__'+morph, head, dep, 'O')) tag = pos+'__'+dep+'__'+morph
Spanish.Defaults.tag_map[tag] = {POS: pos}
tokens.append((id_, word, tag, head, dep, 'O'))
except: except:
raise raise
tuples = [list(t) for t in zip(*tokens)] tuples = [list(t) for t in zip(*tokens)]
@ -65,19 +67,21 @@ def read_conllx(loc, n=0):
break break
def score_model(vocab, encoder, tagger, parser, Xs, ys, verbose=False): def score_model(vocab, encoder, parser, Xs, ys, verbose=False):
scorer = Scorer() scorer = Scorer()
correct = 0. correct = 0.
total = 0. total = 0.
for doc, gold in zip(Xs, ys): for doc, gold in zip(Xs, ys):
doc = Doc(vocab, words=[w.text for w in doc]) doc = Doc(vocab, words=[w.text for w in doc])
encoder(doc) encoder(doc)
tagger(doc)
parser(doc) parser(doc)
PseudoProjectivity.deprojectivize(doc) PseudoProjectivity.deprojectivize(doc)
scorer.score(doc, gold, verbose=verbose) scorer.score(doc, gold, verbose=verbose)
for token, tag in zip(doc, gold.tags): for token, tag in zip(doc, gold.tags):
univ_guess, _ = token.tag_.split('_', 1) if '_' in token.tag_:
univ_guess, _ = token.tag_.split('_', 1)
else:
univ_guess = ''
univ_truth, _ = tag.split('_', 1) univ_truth, _ = tag.split('_', 1)
correct += univ_guess == univ_truth correct += univ_guess == univ_truth
total += 1 total += 1