arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.12828cs.LGcs.DLstat.ML
收藏

CORAL:弱监督Transformers编码表示学习数据分析

CORAL: COde RepresentAtion Learning with Weakly-Supervised Transformers for Analyzing Data Analysis

Peking University(北京大学);University of Washington(华盛顿大学)

Ge Zhang, Mike A. Merrill, Yang Liu, Jeffrey Heer, Tim Althoff

摘要:

对源代码,特别是科学源代码的大规模分析,有望更好地理解数据科学过程,确定分析最佳实践,并为科学工具包的构建者提供见解。然而,大型语料库仍然没有深入分析,因为没有描述性标签,需要专业领域知识来生成。我们提出了一种新的弱监督变换为基础的架构计算联合表示的代码从抽象语法树和周围的自然语言的意见。然后,我们评估了一个新的分类任务,标记计算笔记本细胞的数据分析过程中的阶段,从数据导入到争吵,探索,建模和评估的模型。我们表明,我们的模型,只利用容易获得的弱监督,实现了38%的准确性比专家提供的分析,并优于一套基线。我们的模型使我们能够检查一组118,000字节的笔记本电脑,以揭示常见的数据分析模式。专注于笔记本与学术文章的关系,我们进行了有史以来最大的科学代码的研究,发现笔记本的组成与相应论文的引用计数相关。

英文摘要:

Large scale analysis of source code, and in particular scientific source code, holds the promise of better understanding the data science process, identifying analytical best practices, and providing insights to the builders of scientific toolkits. However, large corpora have remained unanalyzed in depth, as descriptive labels are absent and require expert domain knowledge to generate. We propose a novel weakly supervised transformer-based architecture for computing joint representations of code from both abstract syntax trees and surrounding natural language comments. We then evaluate the model on a new classification task for labeling computational notebook cells as stages in the data analysis process from data import to wrangling, exploration, modeling, and evaluation. We show that our model, leveraging only easily-available weak supervision, achieves a 38% increase in accuracy over expert-supplied heuristics and outperforms a suite of baselines. Our model enables us to examine a set of 118,000 Jupyter Notebooks to uncover common data analysis patterns. Focusing on notebooks with relationships to academic articles, we conduct the largest ever study of scientific code and find that notebook composition correlates with the citation count of corresponding papers.

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。

↑