Finding simplc, non-recursive, base noun phrasc is an important step for many natural language pro-ccssing applications. This paper prescnts a new corpus-based approach using decision tree for that purpose. In contrast to previous methods for Base NP identification, we adopt a decision tree trainedfrom Penn Treebank to identify Base NP. And a self-leaming mechanism is further integrated into our model. Experimental rosults show good performances using our method. The method can also be applied to processing of any other language.