Image-based many-language programming language identification

PeerJ Computer Science

Maurizio Gabbrielli¹  Francesca Del Bonifro¹  Antonio Lategano¹  Stefano Zacchiroli² 

[1] University of Bologna, Bologna, Italy;Université de Paris, Paris, France;

关键词: Programming language identification;    Image recognition;    Machine learning;    Deep learning;    Convolutional neural network;    Code snippet;   

DOI  :  10.7717/peerj-cs.631

来源: DOAJ

【 摘 要 】

Programming language identification (PLI) is a common need in automatic program comprehension as well as a prerequisite for deeper forms of code understanding. Image-based approaches to PLI have recently emerged and are appealing due to their applicability to code screenshots and programming video tutorials. However, they remain limited to the recognition of a small amount of programming languages (up to 10 languages in the literature). We show that it is possible to perform image-based PLI on a large number of programming languages (up to 149 in our experiments) with high (92%) precision and recall, using convolutional neural networks (CNNs) and transfer learning, starting from readily-available pretrained CNNs. Results were obtained on a large real-world dataset of 300,000 code snippets extracted from popular GitHub repositories. By scrambling specific character classes and comparing identification performances we also show that the characters that contribute the most to the visual recognizability of programming languages are symbols (e.g., punctuation, mathematical operators and parentheses), followed by alphabetic characters, with digits and indentation having a negligible impact.

【 授权许可】

Unknown