explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-10 15:14:56 +03:00
Code Issues Packages Projects Releases Wiki Activity

Prepare ArcEager.preprocess_gold to handle subtokens

Browse Source
This commit is contained in:
Matthew Honnibal 2018-04-01 18:03:48 +02:00
parent 2d929ffc5d
commit b8461e71b7
1 changed files with 12 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/syntax/arc_eager.pyx
View File

@ -474,16 +474,21 @@ cdef class ArcEager(TransitionSystem):
def preprocess_gold(self, GoldParse gold): def preprocess_gold(self, GoldParse gold):
if not self.has_gold(gold): if not self.has_gold(gold):
return None return None
for i, (head, dep) in enumerate(zip(gold.heads, gold.labels)): for i, (head_group, dep_group) in enumerate(zip(gold.heads, gold.labels)):
# Missing values # Missing values
if head is None or dep is None: if head_group is None or dep_group is None:
gold.c.heads[i] = i gold.c.heads[i] = i
gold.c.has_dep[i] = False gold.c.has_dep[i] = False
elif isinstance(head, list): continue
# TODO: This is where the fused token stuff will happen if not isinstance(head_group, list):
gold.c.heads[i] = i # Map the simple format into the elaborate one we need for
gold.c.has_dep[i] = False # the fused tokens.
else: head_group = [(head_group, 0)]
dep_group = [dep_group]
for head_addr, dep in zip(head_group, dep_group):
if not isinstance(head_addr, tuple):
head_addr = (head_addr, 0)
head, subtoken = head_addr
if head > i: if head > i:
action = LEFT action = LEFT
elif head < i: elif head < i: