mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-12 10:16:27 +03:00
Add option to control how missing entities are handled when getting NER tags
This commit is contained in:
parent
aff325b7e0
commit
ec63f4fe7b
|
@ -483,7 +483,7 @@ cdef class GoldParse:
|
|||
return not nonproj.is_nonproj_tree(self.heads)
|
||||
|
||||
|
||||
def biluo_tags_from_offsets(doc, entities):
|
||||
def biluo_tags_from_offsets(doc, entities, missing='O'):
|
||||
"""Encode labelled spans into per-token tags, using the Begin/In/Last/Unit/Out
|
||||
scheme (BILUO).
|
||||
|
||||
|
@ -535,7 +535,7 @@ def biluo_tags_from_offsets(doc, entities):
|
|||
if i in entity_chars:
|
||||
break
|
||||
else:
|
||||
biluo[token.i] = 'O'
|
||||
biluo[token.i] = missing
|
||||
return biluo
|
||||
|
||||
|
||||
|
|
Loading…
Reference in New Issue
Block a user