TY - GEN
T1 - Exploring the Use of Natural Language Processing Techniques for Enhancing Genetic Improvement
AU - Krauss, Oliver
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - artificial intelligence
KW - genetic improvement
KW - natural language processing
KW - non-functional properties
UR - http://www.scopus.com/inward/record.url?scp=85168763624&partnerID=8YFLogxK
U2 - 10.1109/GI59320.2023.00014
DO - 10.1109/GI59320.2023.00014
M3 - Conference contribution
AN - SCOPUS:85168763624
T3 - Proceedings - 2023 IEEE/ACM International Workshop on Genetic Improvement, GI 2023
SP - 21
EP - 22
BT - Proceedings - 2023 IEEE/ACM International Workshop on Genetic Improvement, GI 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE/ACM International Workshop on Genetic Improvement, GI 2023
Y2 - 20 May 2023
ER -