Interpretable Program Synthesis

要旨

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 the synthesis. We designed three representations that explain the underlying synthesis process with different levels of fidelity. We implemented an interpretable synthesizer and conducted a within-subjects study with eighteen participants on three challenging regular expression programming tasks. With interpretable synthesis, participants were able to reason about synthesis failures and strategically provide 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.

著者
Tianyi Zhang
Harvard University, Cambridge, Massachusetts, United States
Zhiyang Chen
University of Michigan, Ann Arbor, Michigan, United States
Yuanli Zhu
University of Michigan, Ann Arbor, Michigan, United States
Priyan Vaithilingam
Harvard University, Cambridge, Massachusetts, United States
Xinyu Wang
University of Michigan, Ann Arbor, Michigan, United States
Elena L.. Glassman
Harvard University, Cambridge, Massachusetts, United States
DOI

10.1145/3411764.3445646

論文URL

https://doi.org/10.1145/3411764.3445646

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Engineering Interactive Applications

[B] Paper Room 05, 2021-05-14 01:00:00~2021-05-14 03:00:00 / [C] Paper Room 05, 2021-05-14 09:00:00~2021-05-14 11:00:00 / [A] Paper Room 05, 2021-05-13 17:00:00~2021-05-13 19:00:00
Paper Room 05
14 件の発表
2021-05-14 01:00:00
2021-05-14 03:00:00
日本語まとめ
読み込み中…