Interpretable Program Synthesis
Interpretable Program Synthesis
复制标题
可解释的程序综合
DOI：
10.1145/3411764.3445646
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Elena L. Glassman
中科院分区：
文献类型：
--
作者：
Tianyi Zhang;Zhiyang Chen;Yuanli Zhu;Priyan Vaithilingam;Xinyu Wang;Elena L. Glassman
基于用户提供的规格生成程序的程序合成可能晦涩难懂：用户几乎没有方法可以理解和从合成失败中恢复。我们提出了可解释的程序综合，这是一种揭示合成过程的新颖方法，并使用户能够监视和指导合成器。我们设计了三种表示，以解释具有不同水平的忠诚度的基本合成过程。我们针对正则表达式实施了可解释的合成器，并对十八位参与者进行了三个具有挑战性的正则任务，进行了对象内研究。有了可解释的综合，参与者能够理解合成失败并提供战略反馈，与最先进的合成器相比，成功率明显更高。特别是，参与度较高的参与者（由NCS-6衡量）更喜欢演绎表示，该代表性表示搜索树中的综合过程，而参与者的参与趋势相对较低，偏爱归纳表示，以赋予代表性的计划样本，在合成过程中。
Program synthesis, which generates programs based on user-provided specifications, can be obscure and brittle: users have few ways to understand and recover from synthesis failures. We propose interpretable program synthesis, a novel approach that unveils the synthesis process and enables users to monitor and guide a synthesizer. We designed three representations that explain the underlying synthesis process with different levels of fidelity. We implemented an interpretable synthesizer for regular expressions and conducted a within-subjects study with eighteen participants on three challenging regex tasks. With interpretable synthesis, participants were able to reason about synthesis failures and provide strategic feedback, achieving a significantly higher success rate compared with a state-of-the-art synthesizer. In particular, participants with a high engagement tendency (as measured by NCS-6) preferred a deductive representation that shows the synthesis process in a search tree, while participants with a relatively low engagement tendency preferred an inductive representation that renders representative samples of programs enumerated during synthesis.
影响因子：
--
作者：
Yu Feng;R. Martins;O. Bastani;Işıl Dillig
通讯作者：
Yu Feng;R. Martins;O. Bastani;Işıl Dillig
Scout：通过高级设计约束快速探索界面布局替代方案
DOI：
10.1145/3313831.3376593
发表时间：
2020
期刊：
Proceedings of the CHI Conference on Human Factors in Computing Systems
影响因子：
--
作者：
Swearngin, Amanda;Wang, Chenglong;Oleson, Alannah;Fogarty, James;Ko, Amy J.
通讯作者：
Ko, Amy J.
Wrex：用于为数据科学家合成可读代码的统一示例编程交互
DOI：
10.1145/3313831.3376442
发表时间：
2020
期刊：
CHI 2020
影响因子：
--
作者：
Drosos, Ian;Barik, Titus;Guo, Philip J.;DeLine, Robert;Gulwani, Sumit
通讯作者：
Gulwani, Sumit