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

被引：3

作者：

Krauss, Oliver ^{[1
]}

机构：

[1] Univ Appl Sci Upper Austria, Adv Informat Syst & Technol AIST, Hagenberg, Upper Austria, Austria

来源：

2023 IEEE/ACM INTERNATIONAL WORKSHOP ON GENETIC IMPROVEMENT, GI | 2023年

关键词：

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

D O I：

10.1109/GI59320.2023.00014

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：21 / 22

页数：2

共 8 条

[1] Brown TB, 2020, ADV NEUR IN, V33
[2] Chen Mark, 2021, arXiv, DOI DOI 10.48550/ARXIV.2107.03374
[3] Garg S., 2022, Deepperf: A deep learning-based approach for improving software performance
[4] Dissecting Copy/Delete/Replace/Swap mutations: Insights from a GIN Case Study
Licorish, Sherlock A.
Wagner, Markus
[J]. PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, 2022, : 1940 - 1945
[5] A comparison of bloat control methods for genetic programming
Luke, Sean
Partait, Liviu
[J]. EVOLUTIONARY COMPUTATION, 2006, 14 (03) : 309 - 344
[6] Wang Y, 2021, 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), P8696
[7] Xia C. S, 2022, Less training, more repairing please: Revisiting automated program repair via zeroshot learning
[8] Zong MY, 2022, Arxiv, DOI arXiv:2212.00857

← 1 →