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 18:31:33 +02:00
parent b8461e71b7
commit 5f68e491e1
1 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/syntax/arc_eager.pyx
View File

@ -475,11 +475,11 @@ cdef class ArcEager(TransitionSystem):
if not self.has_gold(gold):
return None
for i, (head_group, dep_group) in enumerate(zip(gold.heads, gold.labels)):
if not USE_SPLIT:
if isinstance(head_group, list):
head_group = [(None, 0)]
dep_group = [None]
# Missing values
if head_group is None or dep_group is None:
gold.c.heads[i] = i
gold.c.has_dep[i] = False
continue
if not isinstance(head_group, list):
# Map the simple format into the elaborate one we need for
# the fused tokens.
@ -489,6 +489,10 @@ cdef class ArcEager(TransitionSystem):
if not isinstance(head_addr, tuple):
head_addr = (head_addr, 0)
head, subtoken = head_addr
if head is None or dep is None:
gold.c.heads[i] = i
gold.c.has_dep[i] = False
continue
if head > i:
action = LEFT
elif head < i:
@ -665,6 +669,8 @@ cdef class ArcEager(TransitionSystem):
# Check label set --- leading cause
label_set = set([self.strings[self.c[i].label] for i in range(self.n_moves)])
for label_str in gold.labels:
if isinstance(label_str, list):
continue
if label_str is not None and label_str not in label_set:
raise ValueError("Cannot get gold parser action: unknown label: %s" % label_str)
# Check projectivity --- other leading cause