一句话：指出大规模开源代码语料使机器学习可行，并以多视角表示学习支撑源代码分析。
编程语言是人工设计、限制严格的受限语言，但源代码本身承担着交流功能：它既要告诉计算机做什么，也要告诉程序员做什么。源代码语法怪异、夹杂大量分隔符，这给自动化处理带来障碍。作者指出一个有利条件：互联网上存在规模极大的开源代码语料，因此把机器学习技术应用于源代码、从而支撑源代码分析是合理且可行的。本文作为特邀教程，围绕这一思路介绍多视角表示学习（multi-perspective representation learning）用于源代码分析：从多个视角为代码学习表示，以服务于下游的代码分析任务。教程侧重阐述研究动机、技术路线与方向展望，摘要中未给出具体的实验设置与评估结果。
Programming languages are artificial and highly restricted languages. But source code is there to tell computers as well as programmers what to do, as an act of communication. Despite its weird syntax and is riddled with different delimiters, the good news is that the very large corpus of open-source code is available. That makes it reasonable to apply machine learning techniques to source code to enable the source code analytics.
DOI 原文 ·
@inproceedings{paperbot7123,
title = {Multi-perspective representation learning for source code analytics (invited tutorial)},
author = {Zhi Jin},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3569446}
}