bug fix

README.md

@@ -29,7 +29,7 @@ class UDgoeswith(object):
   def __call__(self,text):
     import numpy,torch,ufal.chu_liu_edmonds
     w=self.tokenizer(text,return_offsets_mapping=True)
-    v=w["input_ids"]
+    v=[self.tokenizer.cls_token_id]+[t for t,(s,e) in zip(w["input_ids"],w["offset_mapping"]) if s<e]+[self.tokenizer.sep_token_id]
     x=[v[0:i]+[self.tokenizer.mask_token_id]+v[i+1:]+[j] for i,j in enumerate(v[1:-1],1)]
     with torch.no_grad():
       e=self.model(input_ids=torch.tensor(x)).logits.numpy()[:,1:-2,:]