ContraBERT: Enhancing code pre-trained models via contrastive learning

• المؤلفون الرئيسيون: LIU, Shangqing, WU, Bozhi, XIE, Xiaofei, MENG, Guozhu, LIU, Yang.
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2023
• الموضوعات: industries; computer languages; codes; perturbation methods; natural languages; cloning; data augmentation; Artificial Intelligence and Robotics
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8228; https://ink.library.smu.edu.sg/context/sis_research/article/9231/viewcontent/2301.09072.pdf

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple downstream tasks such as clone detection, code search and code transl...