Home > Research > Publications & Outputs > General Program Synthesis using Guided Corpus G...

Electronic data

  • wild19ssbse

    Accepted author manuscript, 1.3 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License


Text available via DOI:

View graph of relations

General Program Synthesis using Guided Corpus Generation and Automatic Refactoring

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Publication date31/08/2019
Host publicationSearch-Based Software Engineering: 11th International Symposium, SSBSE 2019, Tallinn, Estonia, August 31 – September 1, 2019, Proceedings
EditorsShiva Nejati, Gregory Gay
Place of PublicationCham
Number of pages15
ISBN (electronic)9783030274559
ISBN (print)9783030274542
<mark>Original language</mark>English

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (electronic)1611-3349


Program synthesis aims to produce source code based on a user specification, raising the abstraction level of building systems and opening the potential for non-programmers to synthesise their own bespoke services. Both genetic programming (GP) and neural code synthesis have proposed a wide range of approaches to solving this problem, but both have limitations in generality and scope. We propose a hybrid search-based approach which combines (i) a genetic algorithm to autonomously generate a training corpus of programs centred around a set of highly abstracted hints describing interesting features; and (ii) a neural network which trains on this data and automatically refactors it towards a form which makes a more ideal use of the neural network’s representational capacity. When given an unseen program represented as a small set of input and output examples, our neural network is used to generate a rank-ordered search space of what it sees as the most promising programs; we then iterate through this list up to a given maximum search depth. Our results show that this approach is able to find up to 60% of a human-useful target set of programs that it has never seen before, including applying a clip function to the values in an array to restrict them to a given maximum, and offsetting all values in an array.