KoichiYasuoka commited on
Commit
6ef3cd7
1 Parent(s): 0d7556e

aggregation_strategy="simple"

Browse files
Files changed (1) hide show
  1. ud.py +9 -3
ud.py CHANGED
@@ -23,10 +23,16 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
23
  if [0 for i in h if i==0]!=[0]:
24
  m[:,0]+=numpy.where(m[:,0]<numpy.nanmax(m[:,0]),numpy.nan,0)
25
  h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
 
 
 
 
 
 
 
 
26
  t=model_output["sentence"]
27
  u="# text = "+t+"\n"
28
- v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e]
29
  for i,(s,e) in enumerate(v,1):
30
- q=self.model.config.id2label[p[i,h[i]]].split("|")
31
- u+="\t".join([str(i),t[s:e],"_",q[0],"_","|".join(q[1:-1]),str(h[i]),q[-1],"_","_" if i<len(v) and e<v[i][0] else "SpaceAfter=No"])+"\n"
32
  return u+"\n"
 
23
  if [0 for i in h if i==0]!=[0]:
24
  m[:,0]+=numpy.where(m[:,0]<numpy.nanmax(m[:,0]),numpy.nan,0)
25
  h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
26
+ v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e]
27
+ q=[self.model.config.id2label[p[i,j]].split("|") for i,j in enumerate(h)]
28
+ if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]=="simple":
29
+ for i,j in reversed(list(enumerate(q[2:],2))):
30
+ if j[-1]=="goeswith":
31
+ h=[b if i>b else b-1 for a,b in enumerate(h) if i!=a]
32
+ v[i-2]=(v[i-2][0],v.pop(i-1)[1])
33
+ q.pop(i)
34
  t=model_output["sentence"]
35
  u="# text = "+t+"\n"
 
36
  for i,(s,e) in enumerate(v,1):
37
+ u+="\t".join([str(i),t[s:e],"_",q[i][0],"_","|".join(q[i][1:-1]),str(h[i]),q[i][-1],"_","_" if i<len(v) and e<v[i][0] else "SpaceAfter=No"])+"\n"
 
38
  return u+"\n"