Autoencoders as Tools for Program Synthesis

Anonymous

TL;DR: Autoencoder model for absract syntax trees of C++ programs

Abstract:

Recently there have been many advances in research on language modeling of source code.
Applications range from code suggestion and completion to code summarization.
However, complete program synthesis of industry-grade programming languages remains an open problem.
In this work, we introduce and experimentally validate a variational autoencoder model for program synthesis of industry-grade programming languages.
This model makes use of the inherent tree structure of code and can be used in conjunction with gradient free optimization techniques like evolutionary methods to generate programs that maximize a given fitness function, for instance, passing a set of test cases.
A demonstration is avaliable at https://tree2tree.app

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2108.07129/code)