bug fix

README.md

@@ -53,8 +53,9 @@ class TaggerPipeline(TokenClassificationPipeline):
       a2b,b2a=tokenizations.get_alignments(v,text)
       for i,t in enumerate(a2b):
         s,e=(0,0) if t==[] else (t[0],t[-1]+1)
-        if t==[] and v[i]==self.tokenizer.unk_token:
+        if v[i].startswith(self.tokenizer.unk_token):
           s=([[-1]]+[x for x in a2b[0:i] if x>[]])[-1][-1]+1
+        if v[i].endswith(self.tokenizer.unk_token):
           e=([x for x in a2b[i+1:] if x>[]]+[[len(text)]])[0][0]
         d[i]["start"],d[i]["end"]=s,e
     return d