A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes
Computation and Language
2017-04-18 v1
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.
Cite
@article{arxiv.1704.04856,
title = {A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes},
author = {Pablo Loyola and Edison Marrese-Taylor and Yutaka Matsuo},
journal= {arXiv preprint arXiv:1704.04856},
year = {2017}
}
Comments
Accepted at ACL 2017