Exploring the Use of Natural Language Processing Techniques for Enhancing Genetic Improvement

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

3 Citations (Scopus)

Abstract

We explore the potential of using large-scale Natural Language Processing (NLP) models, such as GPT-3, for enhancing genetic improvement in software development. These models have previously been used to automatically find bugs, or improve software. We propose utilizing these models as a novel mutator, as well as for explaining the patches generated by genetic improvement algorithms. Our initial findings indicate promising results, but further research is needed to determine the scalability and applicability of this approach across different programming languages.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/ACM International Workshop on Genetic Improvement, GI 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages21-22
Number of pages2
ISBN (Electronic)9798350312324
DOIs
Publication statusPublished - 2023
Event12th IEEE/ACM International Workshop on Genetic Improvement, GI 2023 - Hybrid, Melbourne, Australia
Duration: 20 May 2023 → …

Publication series

NameProceedings - 2023 IEEE/ACM International Workshop on Genetic Improvement, GI 2023

Conference

Conference12th IEEE/ACM International Workshop on Genetic Improvement, GI 2023
Country/TerritoryAustralia
CityHybrid, Melbourne
Period20.05.2023 → …

Keywords

  • artificial intelligence
  • genetic improvement
  • natural language processing
  • non-functional properties

Fingerprint

Dive into the research topics of 'Exploring the Use of Natural Language Processing Techniques for Enhancing Genetic Improvement'. Together they form a unique fingerprint.

Cite this