DeepDir: a deep learning approach for API directive detection

Jingxuan Zhang, He Jiang, Shuai Lu, Ge Li, Xin Chen

Abstract: API directive is one of the most important knowledge in API specifications. Existing approach only relies on syntactic patterns to detect API directives and lacks a deep semantic understanding. In this study, we propose a deep learning approach DeepDir to automatically detect API directives. Experimental results show that DeepDir significantly improves the state-of-the-art approach by 20.78% on average in terms of F-measure.