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

Fix sent_start multi-task objective when alignment fails

This commit is contained in:
Matthew Honnibal 2018-02-23 16:50:59 +01:00
parent 5fa44e93f1
commit 4492a33a9d
1 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/pipeline.pyx
View File

@ -761,20 +761,19 @@ class MultitaskObjective(Tagger):
sent_tags = ['I-SENT'] * len(words) sent_tags = ['I-SENT'] * len(words)
def _find_root(child): def _find_root(child):
while heads[child] != child: seen = set([child])
if heads[child] is None: while child is not None and heads[child] != child:
if child == 0: seen.add(child)
return child child = heads[child]
else:
child -= 1
else:
child = heads[child]
return child return child
sentences = {} sentences = {}
for i in range(len(words)): for i in range(len(words)):
root = _find_root(i) root = _find_root(i)
sentences.setdefault(root, []).append(i) if root is None:
sent_tags[i] = None
else:
sentences.setdefault(root, []).append(i)
for root, span in sorted(sentences.items()): for root, span in sorted(sentences.items()):
if len(span) == 1: if len(span) == 1:
sent_tags[span[0]] = 'U-SENT' sent_tags[span[0]] = 'U-SENT'