Learning to Synthesize

TL;DR

This paper introduces a flexible framework called learning to synthesis (L2S) that combines syntax, constraints, machine learning, and search algorithms to improve program estimation, demonstrated through automated program repair.

Contribution

The paper proposes the L2S framework, integrating multiple tools for program synthesis, and shows its effectiveness in repairing more bugs than existing methods using only project source code.

Findings

L2S can handle larger search spaces than previous systems.

L2S fixed 4 additional bugs outside ACS's search space.

L2S relies solely on source code from current projects.

Abstract

In many scenarios we need to find the most likely program under a local context, where the local context can be an incomplete program, a partial specification, natural language description, etc. We call such problem program estimation. In this paper we propose an abstract framework, learning to synthesis, or L2S in short, to address this problem. L2S combines four tools to achieve this: syntax is used to define the search space and search steps, constraints are used to prune off invalid candidates at each search step, machine-learned models are used to estimate conditional probabilities for the candidates at each search step, and search algorithms are used to find the best possible solution. The main goal of L2S is to lay out the design space to motivate the research on program estimation. We have performed a preliminary evaluation by instantiating this framework for synthesizing conditions of an automated program repair (APR) system. The training data are from the project itself and related JDK packages. Compared to ACS, a state-of-the-art condition synthesis system for program repair, our approach could deal with a larger search space such that we fixed 4 additional bugs outside the search space of ACS, and relies only on the source code of the current projects.