2019
DOI: 10.1007/978-3-030-27455-9_7
|View full text |Cite
|
Sign up to set email alerts
|

General Program Synthesis Using Guided Corpus Generation and Automatic Refactoring

Abstract: 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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
1
1

Relationship

1
1

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 12 publications
0
1
0
Order By: Relevance
“…We use a Turing-complete language for synthesis (previously used by the authors of [39]), which can be cross-compiled directly into C/Java/Python. Unusually, for general program synthesis, the language features primitive loop operators, variable declarations, and conditional branch operators; a full listing of its operators is given in Appendix A.…”
Section: Target Language and Problem Description Formatmentioning
confidence: 99%
“…We use a Turing-complete language for synthesis (previously used by the authors of [39]), which can be cross-compiled directly into C/Java/Python. Unusually, for general program synthesis, the language features primitive loop operators, variable declarations, and conditional branch operators; a full listing of its operators is given in Appendix A.…”
Section: Target Language and Problem Description Formatmentioning
confidence: 99%