|
Pythia：人工智能辅助代码完成系统
Pythia: AI-assisted Code Completion System |
|
| |
| 课程网址: |
http://videolectures.net/kdd2019_svyatkovskiy_zhao_fu/
|
| 主讲教师: |
Alexey Svyatkovskiy
|
| 开课单位: |
微软
|
| 开课时间: |
2020-03-02
|
| 课程语种: |
英语
|
| 中文简介: |
在本文中，我们提出了一种新的端到端AI辅助代码完成方法，称为Pythia。它生成方法和API建议的排名列表，可供软件开发人员在编辑时使用。该系统当前部署为Visual Studio代码IDE中Intellicode扩展的一部分。Pythia利用从抽象语法树中提取的代码上下文训练的最先进的大规模深度学习模型。它的设计目的是在高吞吐量下预测100毫秒左右的最佳匹配代码完成。
我们描述了系统的体系结构，对基于频率的方法和基于调用的马尔可夫链语言模型进行了比较，并讨论了在轻量级客户端设备上服务Pythia模型的挑战。
在2700个Python开源软件GitHub存储库上获得的离线评估结果显示，前5名的准确率为92%，在项目内部和跨项目设置中，超过了基线模型的平均值20%。
|
| 课程简介: |
In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently deployed as part of Intellicode extension in Visual Studio Code IDE. Pythia exploits state-of-the-art large-scale deep learning models trained on code contexts extracted from abstract syntax trees. It is designed to work at a high throughput predicting the best matching code completions on the order of 100 ms.
We describe the architecture of the system, perform comparisons to frequency-based approach and invocation-based Markov Chain language model, and discuss challenges serving Pythia models on lightweight client devices.
The offline evaluation results obtained on 2700 Python open source software GitHub repositories show a top-5 accuracy of 92%, surpassing the baseline models by 20% averaged over classes, for both intra and cross-project settings.
|
| 关 键 词: |
Pythia; 人工智能辅助代码; 辅助代码完成系统
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2022-09-16：cyh
|
| 最后编审: |
2022-09-19：cyh
|
| 阅读次数: |
31
|
|
图 书 馆