explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-15 14:42:00 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Remove WSD from gold.pyx

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-06 08:43:59 +02:00
parent b61b495024
commit 316a0772b2
1 changed files with 1 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/gold.pyx
View File

@ -144,7 +144,6 @@ def read_json_file(loc, docs_filter=None):
heads = []
labels = []
ner = []
wsd = []
for i, token in enumerate(sent['tokens']):
words.append(token['orth'])
ids.append(i)
@ -155,11 +154,8 @@ def read_json_file(loc, docs_filter=None):
if labels[-1].lower() == 'root':
labels[-1] = 'ROOT'
ner.append(token.get('ner', '-'))
t_wsd = [s.replace('noun.', 'N_').replace('verb.', 'V_')
for s in token.get('ssenses', [])]
wsd.append(t_wsd)
sents.append((
(ids, words, tags, heads, labels, ner, wsd),
(ids, words, tags, heads, labels, ner),
sent.get('brackets', [])))
if sents:
yield (paragraph.get('raw', None), sents)
@ -238,7 +234,6 @@ cdef class GoldParse:
self.heads[i] = self.gold_to_cand[annot_tuples[3][gold_i]]
self.labels[i] = annot_tuples[4][gold_i]
self.ner[i] = annot_tuples[5][gold_i]
self.ssenses[i] = annot_tuples[6][gold_i]
# If we have any non-projective arcs, i.e. crossing brackets, consider
# the heads for those words missing in the gold-standard.