aggregation_strategy="simple"

ud.py

@@ -23,10 +23,16 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
     if [0 for i in h if i==0]!=[0]:
       m[:,0]+=numpy.where(m[:,0]<numpy.nanmax(m[:,0]),numpy.nan,0)
       h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
+    v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e]
+    q=[self.model.config.id2label[p[i,j]].split("|") for i,j in enumerate(h)]
+    if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]=="simple":
+      for i,j in reversed(list(enumerate(q[2:],2))):
+        if j[-1]=="goeswith":
+          h=[b if i>b else b-1 for a,b in enumerate(h) if i!=a]
+          v[i-2]=(v[i-2][0],v.pop(i-1)[1])
+          q.pop(i)
     t=model_output["sentence"]
     u="# text = "+t+"\n"
-    v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e]
     for i,(s,e) in enumerate(v,1):
-      q=self.model.config.id2label[p[i,h[i]]].split("|")
-      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"
+      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"
     return u+"\n"