Computing the differences between two versions of the same program is an essential task for software development and software evolution research. AST differencing is the most advanced way of doing so, and an active research area. Yet, AST differencing still relies on default configurations or manual tweaking. In this paper we present a novel approach named DAT for hyperparameter optimization of AST differencing. We thoroughly state the problem of hyper configuration for AST differencing. We show that our data-driven approach to hyperoptimize AST differencing systems increases the edit-script quality in up to 53% of cases.

中文翻译：

---

AST差异的超参数优化

计算同一程序的两个版本之间的差异是软件开发和软件演化研究的基本任务。AST区分是最先进的方法，也是活跃的研究领域。但是，AST差异仍然依赖于默认配置或手动调整。在本文中，我们提出了一种名为DAT的新颖方法，用于AST差分的超参数优化。我们彻底陈述了AST差异的超配置问题。我们表明，我们的数据驱动方法可以对AST差异系统进行超优化，从而在多达53％的情况下提高了编辑脚本的质量。