已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search

计算机科学 自动汇总 源代码 代码评审 KPI驱动的代码分析 人工智能 程序设计语言 语义学(计算机科学) 静态程序分析 编码(集合论) 自然语言 情报检索 理论计算机科学 软件 软件开发 集合(抽象数据类型)
作者
Shangqing Liu,Xiaofei Xie,Jingkai Siow,Lei Ma,Guozhu Meng,Yang Liu
出处
期刊:IEEE Transactions on Software Engineering [IEEE Computer Society]
卷期号:49 (4): 2839-2855 被引量:38
标识
DOI:10.1109/tse.2022.3233901
摘要

Code search aims to retrieve accurate code snippets based on a natural language query to improve software productivity and quality. With the massive amount of available programs such as (on GitHub or Stack Overflow), identifying and localizing the precise code is critical for the software developers. In addition, Deep learning has recently been widely applied to different code-related scenarios, e.g., vulnerability detection, source code summarization. However, automated deep code search is still challenging since it requires a high-level semantic mapping between code and natural language queries. Most existing deep learning-based approaches for code search rely on the sequential text i.e., feeding the program and the query as a flat sequence of tokens to learn the program semantics while the structural information is not fully considered. Furthermore, the widely adopted Graph Neural Networks (GNNs) have proved their effectiveness in learning program semantics, however, they also suffer the problem of capturing the global dependencies in the constructed graph, which limits the model learning capacity. To address these challenges, in this paper, we design a novel neural network framework, named GraphSearchNet, to enable an effective and accurate source code search by jointly learning the rich semantics of both source code and natural language queries. Specifically, we propose to construct graphs for the source code and queries with bidirectional GGNN (BiGGNN) to capture the local structural information of the source code and queries. Furthermore, we enhance BiGGNN by utilizing the multi-head attention module to supplement the global dependencies that BiGGNN missed to improve the model learning capacity. The extensive experiments on Java and Python programming language from the public benchmark CodeSearchNet confirm that GraphSearchNet outperforms current state-of-the-art works by a significant margin.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
胖球发布了新的文献求助10
2秒前
风一样的我完成签到 ,获得积分0
2秒前
3秒前
huahuahua发布了新的文献求助10
4秒前
4秒前
cdercder的应助被fengjingjing采纳,获得10
5秒前
Lyy关闭了Lyy的文献求助
5秒前
今后的应助被fengjingjing采纳,获得10
5秒前
tian发布了新的文献求助30
10秒前
11秒前
h123完成签到,获得积分10
12秒前
12秒前
搜集达人的应助被科研通管家采纳,获得10
14秒前
深情安青的应助被科研通管家采纳,获得10
14秒前
DW的应助被科研通管家采纳,获得10
14秒前
14秒前
xinyuanjia的应助被科研通管家采纳,获得30
14秒前
CipherSage的应助被科研通管家采纳,获得10
15秒前
领导范儿的应助被Zzzzzzz采纳,获得10
15秒前
Akim的应助被科研通管家采纳,获得10
15秒前
星辰大海的应助被科研通管家采纳,获得10
15秒前
桐桐的应助被科研通管家采纳,获得10
15秒前
桐桐的应助被科研通管家采纳,获得10
15秒前
15秒前
huahuahua发布了新的文献求助10
15秒前
无花果的应助被科研通管家采纳,获得10
15秒前
bkagyin的应助被科研通管家采纳,获得10
15秒前
ding的应助被科研通管家采纳,获得10
16秒前
16秒前
DW的应助被科研通管家采纳,获得10
16秒前
16秒前
artemis发布了新的文献求助100
17秒前
乐空思的应助被纯真的坤采纳,获得10
17秒前
kxy0311完成签到 ,获得积分10
17秒前
爱学习的白树完成签到 ,获得积分10
17秒前
福斯卡完成签到 ,获得积分10
18秒前
科研通AI6.2的应助被xiaoyu采纳,获得10
19秒前
11号yan完成签到 ,获得积分10
19秒前
20秒前
Akim的应助被yy采纳,获得10
20秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8189808
求助须知:如何正确求助?哪些是违规求助? 9576985
关于积分的说明 21850907
捐赠科研通 7787770
什么是DOI,文献DOI怎么找? 3435793
关于科研通互助平台的介绍 2559825
邀请新用户注册赠送积分活动 2482680