Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix entity IOB and tag in span merging

This commit is contained in:
Matthew Honnibal 2018-03-25 22:16:01 +02:00
parent 5430c43298
commit 8e08c378fe
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/tokens/doc.pyx
View File

@ -460,10 +460,7 @@ cdef class Doc:
cdef int i cdef int i
for i in range(self.length): for i in range(self.length):
self.c[i].ent_type = 0 self.c[i].ent_type = 0
# At this point we don't know whether the NER has run over the self.c[i].ent_iob = 2 # Means O. Non-O are set from ents.
# Doc. If the ent_iob is missing, leave it missing.
if self.c[i].ent_iob != 0:
self.c[i].ent_iob = 2 # Means O. Non-O are set from ents.
cdef attr_t ent_type cdef attr_t ent_type
cdef int start, end cdef int start, end
for ent_info in ents: for ent_info in ents:
@ -978,6 +975,8 @@ cdef class Doc:
self.c[i].head = start self.c[i].head = start
elif head_idx >= end: elif head_idx >= end:
self.c[i].head -= offset self.c[i].head -= offset
token.ent_iob = span[0].ent_iob
token.ent_type = span[0].ent_type
# Now compress the token array # Now compress the token array
for i in range(end, self.length): for i in range(end, self.length):
self.c[i - offset] = self.c[i] self.c[i - offset] = self.c[i]
@ -988,6 +987,7 @@ cdef class Doc:
for i in range(self.length): for i in range(self.length):
# ...And, set heads back to a relative position # ...And, set heads back to a relative position
self.c[i].head -= i self.c[i].head -= i
# TODO: Fix entity IOB
# Set the left/right children, left/right edges # Set the left/right children, left/right edges
set_children_from_heads(self.c, self.length) set_children_from_heads(self.c, self.length)
# Clear the cached Python objects # Clear the cached Python objects