explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-06 14:13:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix loading of gold morphology

Browse Source
This commit is contained in:
Matthew Honnibal 2018-09-26 21:01:48 +02:00
parent 2be15fa7d2
commit 3b6b018904
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/gold.pyx
View File

@ -429,17 +429,17 @@ cdef class GoldParse:
if words is None: if words is None:
words = [token.text for token in doc] words = [token.text for token in doc]
if tags is None: if tags is None:
tags = [None for _ in doc] tags = [None for _ in words]
if heads is None: if heads is None:
heads = [None for token in doc] heads = [None for token in words]
if deps is None: if deps is None:
deps = [None for _ in doc] deps = [None for _ in words]
if entities is None: if entities is None:
entities = [None for _ in doc] entities = [None for _ in words]
if morphology is None: if morphology is None:
morphology = [None for _ in doc] morphology = [None for _ in words]
elif len(entities) == 0: elif len(entities) == 0:
entities = ['O' for _ in doc] entities = ['O' for _ in words]
elif not isinstance(entities[0], basestring): elif not isinstance(entities[0], basestring):
# Assume we have entities specified by character offset. # Assume we have entities specified by character offset.
entities = biluo_tags_from_offsets(doc, entities) entities = biluo_tags_from_offsets(doc, entities)
@ -532,6 +532,7 @@ cdef class GoldParse:
else: else:
self.words[i] = words[gold_i] self.words[i] = words[gold_i]
self.tags[i] = tags[gold_i] self.tags[i] = tags[gold_i]
self.morphology[i] = morphology[gold_i]
if heads[gold_i] is None: if heads[gold_i] is None:
self.heads[i] = None self.heads[i] = None
else: else: