arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.09495cs.SEcs.AI
收藏

Topical:利用注意力机制从源代码中学习仓库嵌入

Topical: Learning Repository Embeddings from Source Code using Attention

JPMorgan Chase(摩根大通)

Agathe Lherondelle, Varun Babbar, Yash Satsangi, Fran Silavong, Shaltiel Eloul, Sean Moran

AI总结:

本研究提出新型深度神经网络Topical,借助注意力机制融合源代码、依赖图与脚本文本生成仓库级嵌入,在GitHub仓库训练后于自动标注等任务超越多个基线,兼具可扩展性与高效性,相关资源已开源。

摘要:

本文提出Topical,一种用于仓库级嵌入的新型深度神经网络。现有方法依赖自然语言文档或朴素聚合技术,Topical通过注意力机制的应用表现更优。该机制从源代码、完整依赖图以及脚本级文本数据生成仓库级表示。Topical在可公开访问的GitHub仓库上训练,在仓库自动标注等任务中超越多个基线,凸显了注意力机制相较于传统聚合方法的有效性。Topical还具备可扩展性与高效性,为仓库级表示计算提供了有价值的贡献。相关工具、代码与训练数据集已发布于https://github.com/jpmorganchase/topical,可供后续研究使用。

英文摘要:

This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation techniques, are outperformed by Topical's utilization of an attention mechanism. This mechanism generates repository-level representations from source code, full dependency graphs, and script level textual data. Trained on publicly accessible GitHub repositories, Topical surpasses multiple baselines in tasks such as repository auto-tagging, highlighting the attention mechanism's efficacy over traditional aggregation methods. Topical also demonstrates scalability and efficiency, making it a valuable contribution to repository-level representation computation. For further research, the accompanying tools, code, and training dataset are provided at: https://github.com/jpmorganchase/topical.

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。

↑