A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes

Abstract

We propose a model to automatically describe changes introduced in the source code of a program using natural language. Our method receives as input a set of code commits, which contains both the modifications and message introduced by an user. These two modalities are used to train an encoder-decoder architecture. We evaluated our approach on twelve real world open source projects from four different programming languages. Quantitative and qualitative results showed that the proposed approach can generate feasible and semantically sound descriptions not only in standard in-project settings, but also in a cross-project setting.

Accepted at ACL 2017

References in corpus (2)

• Recurrent Neural Network Regularization
• Convolutional Neural Networks over Tree Structures for Programming Language Processing

Cited by in corpus (7)

• Towards Neural Decompilation
• Generating Commit Messages from Git Diffs
• On the Relevance of Cross-project Learning with Nearest Neighbours for Commit Message Generation
• Source Code Comments: Overlooked in the Realm of Code Clone Detection
• Pointing to Subwords for Generating Function Names in Source Code
• Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation
• A Multi-Modal Transformer-based Code Summarization Approach for Smart Contracts