程序表示学习综述  

Survey on program representation learning

作　　者：马骏驰 迪骁鑫 段宗涛[1] 唐蕾[1] MA Jun-chi;DI Xiao-xin;DUAN Zong-tao;TANG Lei(College of Information Engineering,Chang’an University,Xi’an 710064,China)

机构地区：[1]长安大学信息工程学院,陕西西安710064

出　　处：《浙江大学学报（工学版）》2023年第1期155-169,共15页Journal of Zhejiang University：Engineering Science

基　　金：国家自然基金青年资助项目(62002030);陕西省重点研发资助项目(2019ZDLGY17-08,2019ZDLGY03-09-01,2019GY-006,2020GY-013)。

摘　　要：为了提高软件的开发效率,目前已出现应用人工智能技术进行智能化开发的趋势,如何理解程序语义是智能化开发中需要重点解决的问题.针对该问题,出现了一系列程序表示学习的研究,程序表示学习可以自动地从程序中学习有用的特征,将特征表示为低维稠密向量,高效地提取程序语义并使用于相应的下游任务.对程序表示学习的研究工作进行综述,介绍了主流的程序表示学习模型,包括基于图结构和基于token序列的程序表示学习框架.展示了程序表示学习技术在缺陷检测、缺陷定位、代码补全等任务上的应用,总结了程序表示学习的常用工具集和测试集.分析了程序表示学习未来需要应对的挑战.There has been a trend of intelligent development using artificial intelligence technology in order to improve the efficiency of software development. It is important to understand program semantics to support intelligent development. A series of research work on program representation learning has emerged to solve the problem. Program representation learning can automatically learn useful features from programs and represent the features as low-dimensional dense vectors in order to efficiently extract program semantic and apply it to corresponding downstream tasks. A comprehensive review to categorize and analyze existing research work of program representation learning was provided. The mainstream models for program representation learning were introduced, including the frameworks based on graph structure and token sequence. Then the applications of program representation learning technology in defect detection, defect localization, code completion and other tasks were described. The common toolsets and benchmarks for program representation learning were summarized. The challenges for program representation learning in the future were analyzed.

关 键 词：软件工程 表示学习 程序语义 神经网络 深度学习 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论] TP18[自动化与计算机技术—计算机科学与技术]