- author = "Oumaima {Bel Moudden} and Rym Guibadj and Denis Robilliard and Cyril Fonlupt and Abdeslam Kadrani and Rachid Benmansour",
- title = "A re-assessment of {Code2Vec}",
- booktitle = "MAIDSS'24: Modern Artificial Intelligence and Data Science Systems",
- year = "2024",
- editor = "Abdellah Idrissi",
- volume = "1166",
- series = "Studies in Computational Intelligence",
- pages = "133--140",
- address = "Rabat, Morocco",
- month = feb # " 13-14",
- publisher = "Springer Nature",
- keywords = "genetic algorithms, genetic programming, Source code analysis, Code representation, Code2Vec, Code embedding, training, GitHub",
- hal_id = "hal-05461814",
- hal_version = "v1",
-
URL = "
https://hal.science/hal-05461814",
- pdf = "https://hal.science/hal-05461814v1/file/Maidss24__A_re_assessment_of_Code2Vec%20%281%29.pdf",
-
DOI = "
10.1007/978-3-031-65038-3_10",
- size = "8 pages",
- abstract = "Code2Vec has emerged as a powerful tool for analyzing source code by leveraging distributed representations. Code2Vec has demonstrated substantial capabilities in capturing semantic information from source code; however, its sensitivity to variable names has been identified as a significant limitation. This sensitivity raises concerns about the robustness of the models performance in different code bases with varying naming conventions. In response to this limitation, our study focuses on evaluating the impact of a variable name anonymisation technique. The anonymisation process was guided by the fundamental concept that a program semantics remain consistent despite changes in variable names. This idea underscores the potential for exploring Code2Vecs learning performance with anonymous variables. As operations within a program constitute its semantics, and certain paths encapsulate these operations, it prompts a natural inquiry into whether Code2Vec learning process can be enhanced by prioritising operations over variable names. By anonymizing variable names, we aim to enhance Code2Vec's generalization performance, especially when confronted with non-human-generated source code, such as that produced by genetic programming.",
-
notes = "
https://easychair.org/cfp/maidss24
Univ. Littoral Cote d'Opale, UR 4491, LISIC, Laboratoire d'Informatique Signal et Image de la Cote d'Opale, Calais, France",
