algorithm improved

ud.py

@@ -12,10 +12,13 @@ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
     x=self.model.config.label2id
     y=[k for k in x if k.find("|")<0 and not k.startswith("I-")]
     self.transition=numpy.full((len(x),len(x)),-numpy.inf)
+    self.sympos=numpy.full((len(x)),-numpy.inf)
     for k,v in x.items():
       if k.find("|")<0:
         for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
           self.transition[v,x[j]]=0
+        if k.startswith("SYM"):
+          self.sympos[v]=0
   def check_model_type(self,supported_models):
     pass
   def postprocess(self,model_outputs,**kwargs):
@@ -24,14 +27,18 @@ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
     return self.bellman_ford_token_classification(model_outputs,**kwargs)
   def bellman_ford_token_classification(self,model_outputs,**kwargs):
     m=model_outputs["logits"][0].numpy()
+    v=model_outputs["offset_mapping"][0].tolist()
     e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
     z=e/e.sum(axis=-1,keepdims=True)
     for i in range(m.shape[0]-1,0,-1):
-      m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
+      if v[i-1][0]<v[i-1][1]:
+        m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
+      else:
+        m[i-1]+=self.sympos
     k=[numpy.argmax(m[0]+self.transition[0])]
     for i in range(1,m.shape[0]):
       k.append(numpy.argmax(m[i]+self.transition[k[-1]]))
-    w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
+    w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(v,k)) if s<e]
     if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
       for i,t in reversed(list(enumerate(w))):
         p=t.pop("entity")