Modular Tree Network for Source Code Representation Learning

by   Wenhan Wang, et al.

Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing models did not make full use of the unique structural information of programs. Although abstract syntax tree-based neural models can handle the tree structure in the source code, they cannot capture the richness of different types of substructure in programs. In this paper, we propose a modular tree network (MTN) which dynamically composes different neural network units into tree structures based on the input abstract syntax tree. Different from previous tree-structural neural network models, MTN can capture the semantic differences between types of ASTsubstructures. We evaluate our model on two tasks: program classification and code clone detection. Ourmodel achieves the best performance compared with state-of-the-art approaches in both tasks, showing the advantage of leveraging more elaborate structure information of the source code.


page 1

page 2

page 3

page 4


Program Classification Using Gated Graph Attention Neural Network for Online Programming Service

The online programing services, such as Github,TopCoder, and EduCoder, h...

Learning to Represent Programs with Heterogeneous Graphs

Program source code contains complex structure information, which can be...

Code Representation Learning with Prüfer Sequences

An effective and efficient encoding of the source code of a computer pro...

Retrieval-Based Neural Code Generation

In models to generate program source code from natural language, represe...

Automatic Repair and Type Binding of Undeclared Variables using Neural Networks

Deep learning had been used in program analysis for the prediction of hi...

Please sign up or login with your details

Forgot password? Click here to reset