arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.02715cs.SEstat.ML
收藏

软件代码的深层语言模型

A deep language model for software code

Hoa Khanh Dam, Truyen Tran, Trang Pham

摘要:

现有的语言模型,如软件代码的n-gram,通常无法捕获依赖代码元素分散得很远的长上下文。在本文中,我们提出了一种新的方法来建立一个语言模型的软件代码,以解决这个特殊的问题。我们的语言模型部分受到人类记忆的启发,建立在强大的基于深度学习的长短期记忆架构之上,该架构能够学习软件代码中经常出现的长期依赖关系。我们的内在评价的Java项目语料库的结果表明,我们的语言模型的有效性。这项工作有助于实现我们对DeepSoft的愿景,DeepSoft是一个端到端的,通用的基于深度学习的框架,用于建模软件及其开发过程。

英文摘要:

Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart. In this paper, we propose a novel approach to build a language model for software code to address this particular issue. Our language model, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term dependencies which occur frequently in software code. Results from our intrinsic evaluation on a corpus of Java projects have demonstrated the effectiveness of our language model. This work contributes to realizing our vision for DeepSoft, an end-to-end, generic deep learning-based framework for modeling software and its development process.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑