Blogs (1) >>
ICSE 2019
Sat 25 - Fri 31 May 2019 Montreal, QC, Canada
Fri 31 May 2019 11:40 - 12:00 at Place du Canada - Machine Learning in Static Analysis Chair(s): Na Meng

Exploiting machine learning techniques for analyzing programs has attracted much attention. One key problem is how to represent code fragments well for follow-up analysis. Traditional information retrieval based methods often treat programs as natural language texts, which could miss important semantic information of source code. Recently, state-of-the-art studies demonstrate that abstract syntax tree (AST) based neural models can better represent source code. However, the sizes of ASTs are usually large and the existing models are prone to the long-term dependency problem. In this paper, we propose a novel AST-based Neural Network (ASTNN) for source code representation. Unlike existing models that work on entire ASTs, ASTNN splits each large AST into a sequence of small statement trees, and recursively encodes the statement trees to vectors by capturing the lexical and syntactical knowledge of statements. Based on the sequence of statement vectors, a bidirectional RNN model is used to leverage the naturalness of statements and finally produce the vector representation of a code fragment. We have applied our neural network based source code representation method to two common program comprehension tasks: source code classification and code clone detection. Experimental results on the two tasks indicate that our model is superior to state-of-the-art approaches.

Fri 31 May
Times are displayed in time zone: Eastern Time (US & Canada) change

11:00 - 12:30: Machine Learning in Static AnalysisPapers / Technical Track at Place du Canada
Chair(s): Na MengVirginia Tech
11:00 - 11:20
Talk
Technical Track
Facundo MolinaUniversidad Nacional de Rio Cuarto, Argentina, Renzo DegiovanniSnT, University of Luxembourg, Pablo PonzioDept. of Computer Science FCEFQyN, University of Rio Cuarto, Germán RegisUniversidad Nacional de Río Cuarto, Nazareno AguirreDept. of Computer Science FCEFQyN, University of Rio Cuarto, Marcelo F. FriasDept. of Software Engineering Instituto Tecnológico de Buenos Aires
11:20 - 11:40
Talk
Technical Track
Ming FanMOEKLINNS Lab, Department of Computer Science and Technology, Xi'an Jiaotong University, 710049, China, Xiapu Luo, Jun LiuMOEKLINNS Lab, Department of Computer Science and Technology, Xi'an Jiaotong University, 710049, China, Meng WangUniversity of Bristol, UK, Chunyin Nong, Qinghua ZhengMOEKLINNS Lab, Department of Computer Science and Technology, Xi'an Jiaotong University, 710049, China, Ting LiuMOEKLINNS Lab, Department of Computer Science and Technology, Xi'an Jiaotong University, 710049, China
11:40 - 12:00
Talk
Technical Track
Jian ZhangBeihang University, Xu WangBeihang University, Hongyu ZhangThe University of Newcastle, Hailong SunBeihang University, Kaixuan WangBeihang University, Xudong LiuBeihang University
Pre-print
12:00 - 12:20
Talk
Technical Track
Alexander LeClairUniversity Of Notre Dame, Siyuan JiangEastern Michigan University, Collin McMillan
12:20 - 12:30
Talk
Papers