explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-05 14:10:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Filter out uannotated sentences in NER

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-23 22:58:49 +02:00
parent 420a986d15
commit ca608467da
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/syntax/ner.pyx
View File

@ -130,6 +130,7 @@ cdef class BiluoPushDown(TransitionSystem):
return MOVE_NAMES[move] + '-' + self.strings[label]
def init_gold_batch(self, examples):
examples = [eg for eg in examples if self.has_gold(eg)]
states = self.init_batch([eg.predicted for eg in examples])
keeps = [i for i, s in enumerate(states) if not s.is_final()]
states = [states[i] for i in keeps]
@ -237,6 +238,9 @@ cdef class BiluoPushDown(TransitionSystem):
self.add_action(UNIT, st._sent[i].ent_type)
self.add_action(LAST, st._sent[i].ent_type)
def has_gold(self, Example eg):
return eg.y.is_nered
def get_cost(self, StateClass stcls, gold, int i):
if not isinstance(gold, BiluoGold):
raise TypeError("Expected BiluoGold")