Feedback-driven semi-supervised synthesis of program transformations

While editing code, it is common for developers to make multiple related repeated edits that are all instances of a more general program transformation. Since this process can be tedious and error-prone, we study the problem of automatically learning program transformations from past edits, which ca...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of ACM on programming languages Vol. 4; no. OOPSLA; pp. 1 - 30
Main Authors: Gao, Xiang, Barke, Shraddha, Radhakrishna, Arjun, Soares, Gustavo, Gulwani, Sumit, Leung, Alan, Nagappan, Nachiappan, Tiwari, Ashish
Format: Journal Article
Language:English
Published: New York, NY, USA ACM 13.11.2020
Subjects:
Artificial intelligence
Automatic programming
Computing methodologies
Development frameworks and environments
Integrated and visual development environments
Software and its engineering
Software creation and management
Software development techniques
Software maintenance tools
Software notations and tools
Programming by Example
Program synthesis
Refactoring
Program transformation
ISSN:2475-1421, 2475-1421
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While editing code, it is common for developers to make multiple related repeated edits that are all instances of a more general program transformation. Since this process can be tedious and error-prone, we study the problem of automatically learning program transformations from past edits, which can then be used to predict future edits. We take a novel view of the problem as a semi-supervised learning problem: apart from the concrete edits that are instances of the general transformation, the learning procedure also exploits access to additional inputs (program subtrees) that are marked as positive or negative depending on whether the transformation applies on those inputs. We present a procedure to solve the semi-supervised transformation learning problem using anti-unification and programming-by-example synthesis technology. To eliminate reliance on access to marked additional inputs, we generalize the semi-supervised learning procedure to a feedback-driven procedure that also generates the marked additional inputs in an iterative loop. We apply these ideas to build and evaluate three applications that use different mechanisms for generating feedback. Compared to existing tools that learn program transformations from edits, our feedback-driven semi-supervised approach is vastly more effective in successfully predicting edits with significantly lesser amounts of past edit data.
ISSN:2475-1421
2475-1421
DOI:10.1145/3428287