基于源代码的机器学习
ML4CODE
本领域主要关注三方面问题：
* 代码生成
* 代码表示
* 模式识别CodRep
代码表示学习的比赛，给定源代码，要求修补源代码中的bug
论文
程序生成
Synthetic Datasets for Neural Program Synthesis, ICLR 2019
Execution-Guided Neural Program Synthesis, ICLR 2019
DeepFuzz: Automatic Generation of Syntax Valid C Programs for Fuzz Testing,
AAAI 2019
Towards Synthesizing Complex Programs from Input-Output Examples, ICLR 2018
源代码分析及语言模型
Generative Code Modeling with Graphs, ICLR 2019
NL2Type: Inferring JavaScript Function Types from Natural Language
Information, ICSE 2019
A Novel Neural Source Code Representation based on Abstract Syntax Tree, ICSE
2019
Deep Learning Type Inference, FSE 2018
Learning to Represent Programs with Graphs, ICLR 2018
Are Deep Neural Networks the Best Choice for Modeling Source Code?, FSE 2017
神经网络结构与算法
Neural Code Comprehension: A Learnable Representation of Code Semantics,
NeurIPS 2018
A General Path-Based Representation for Predicting Program Properties, PLDI
2018
Cross-Language Learning for Program Classification using Bilateral Tree-Based
Convolutional Neural Networks, AAAI 2018
嵌入
A Literature Study of Embeddings on Source Code, arxiv
Deep Code Search, ICSE 2018
Code Vectors: Understanding Programs Through Embedded Abstracted Symbolic
Traces, FSE 2018
程序翻译
Towards Neural Decompilation, arxiv
Tree-to-tree Neural Networks for Program Translation, ICLR 2018
Code Attention: Translating Code to Comments by Exploiting Domain Features,
arxiv
代码补全
Aroma: Code Recommendation via Structural Code Search, arxiv
程序修复
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability
Detection, ICLR 2019
Neural Program Repair by Jointly Learning to Localize and Repair, ICLR 2019
Dynamic Neural Program Embedding for Program Repair, ICLR 2018
模式识别
SAR: Learning Cross-Language API Mappings with Little Knowledge, FSE 2019
Hierarchical Learning of Cross-Language Mappings through Distributed Vector
Representations for Code, ICSE 2018
Deep API Learning, FSE 2016
代码优化
Neural Nets Can Learn Function Type Signatures From Binaries, USENIX 2017
代码总结
Summarizing Source Code with Transferred API Knowledge, IJCAI 2018
A Neural Framework for Retrieval and Summarization of Source Code, ASE 2018