BriefGPT.xyz
Apr, 2020
语言模型生成的源代码嵌入
SCELMo: Source Code Embeddings from Language Models
HTML
PDF
Rafael - Michael Karampatsis, Charles Sutton
TL;DR
本文提出了一种基于语言模型的深度上下文化单词表征，通过使用ELMo框架训练这些嵌入来研究其在下游缺陷检测任务中的有效性，并表明即使在相对较小的代码库中，低维度的嵌入也可以改进最先进的机器学习系统进行缺陷检测。
Abstract
continuous embeddings
of tokens in computer programs have been used to support a variety of software development tools, including readability, code search, and program repair.
contextual embeddings
are common in
→