Augmenting Java method comments generation with context information based on neural networks
Augmenting Java method comments generation with context information based on neural networks
复制标题
基于神经网络的上下文信息增强 Java 方法注释生成
DOI:
10.1016/j.jss.2019.07.087
复制
发表时间:
2019-07
影响因子:
3.5
通讯作者:
Huang Zhiqiu
中科院分区:
文献类型:
--
作者:
Zhou Yu;Yan Xin;Yang Wenhua;Chen Taolue;Huang Zhiqiu
Code comments are crucial to program comprehension. In this paper, we propose a novel approach ContextCC to automatically generate concise comments for Java methods based on neural networks, leveraging techniques of program analysis and natural language processing. Firstly, ContextCC employs program analysis techniques, especially abstract syntax tree parsing, to extract context information including methods and their dependency. Secondly, it filters code and comments out of the context information to build up a high-quality data set based on a set of pre-defined templates and rules. Finally, ContextCC trains a code comment generation model based on recurrent neural networks. Experiments are conducted on Java projects crawled from GitHub. We show empirically that the performance of ContextCC is superior to state-of-the-art baseline methods.
登录
查看更多内容
DOI:
10.18653/v1/p16-2
发表时间:
2016
期刊:
--
影响因子:
--
作者:
K. Erk;Noah A. Smith
通讯作者:
K. Erk;Noah A. Smith
影响因子:
7.4
作者:
Yu Zhou;Changzhi Wang;Xin Yan;Taolue Chen;Sebastiano Panichella;Harald Gall
通讯作者:
Harald Gall
DOI:
10.1109/icse.2017.11
发表时间:
2017-05
期刊:
2017 IEEE/ACM 39th International Conference on Software Engineering (ICSE)
影响因子:
--
作者:
Yu Zhou;Ruihang Gu;Taolue Chen;Zhiqiu Huang;Sebastiano Panichella;H. Gall
通讯作者:
Yu Zhou;Ruihang Gu;Taolue Chen;Zhiqiu Huang;Sebastiano Panichella;H. Gall
DOI:
10.1109/icpc.2011.28
发表时间:
2011-06
期刊:
2011 IEEE 19th International Conference on Program Comprehension
影响因子:
--
作者:
G. Sridhara;L. Pollock;K. Vijay-Shanker
通讯作者:
G. Sridhara;L. Pollock;K. Vijay-Shanker
DOI:
10.1145/1985441.1985471
发表时间:
2011-05
期刊:
--
影响因子:
--
作者:
D. Binkley;Matthew Hearn;Dawn J Lawrie
通讯作者:
D. Binkley;Matthew Hearn;Dawn J Lawrie