Utilizing AI Approaches for Generating Code Automatically
Article Sidebar
Main Article Content
Abstract — The use of artificial intelligence (AI) to automatically generate code is transforming the way software is developed. By speeding up the coding process and minimizing mistakes that humans often make, AI-powered tools are helping developers work more efficiently and creatively. This paper takes a closer look at different AI techniques used for automatic code generation, including traditional machine learning methods, advanced deep learning models, and natural language processing (NLP) approaches that enable computers to understand and produce human language.
Recent breakthroughs, especially with transformer-based models, have led to powerful tools like GitHub Copilot, which can assist programmers by suggesting code snippets in real time. We explore how these technologies work, their advantages, and the challenges they still face - such as handling complex programming tasks or understanding context deeply. Finally, this paper discusses open questions and promising directions for future research, as this exciting field continues to evolve quickly.
Downloads
References
Allamanis, M., Barr, E. T., Devanbu, P., & Sutton, C. (2018). A survey of machine learning for big code and naturalness. ACM Computing Surveys, 51(4), 1-37. https://doi.org/10.1145/3212695
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877-1901.
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P., Kaplan, J., ... & Zaremba, W. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374.
Gupta, S., Pal, S., Kanade, A., & Shevade, S. (2018). Deepfix: Fixing common C language errors by deep learning. AAAI Conference on Artificial Intelligence, 1345-1351.
Zao, K., Wang, Y., & Li, J. (2021). Ethical considerations in AI-generated code. Proceedings of the ACM on Programming Languages, 5(ICFP), 1-23.
Hu, X., Li, G., Xia, X., Lo, D., & Jin, Z. (2018). Deep code comment generation. Proceedings of the 26th International Conference on Program Comprehension, 200-210.
Mernik, M., Heering, J., & Sloane, A. M. (2005). When and how to develop domain-specific languages. ACM Computing Surveys, 37(4), 316-344. https://doi.org/10.1145/1118890.1118892
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Blog.
Raychev, V., Bielik, P., & Vechev, M. (2016). Probabilistic model for code with decision trees. ACM SIGPLAN Notices, 51(10), 731-747.
Tufano, M., Watson, C., Bavota, G., Penta, M. D., Oliveto, R., & Poshyvanyk, D. (2019). An empirical study on learning bug-fixing patches in the wild via neural machine translation. IEEE Transactions on Software Engineering, 47(9), 1920-1940.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 5998-6008.
Yin, P., & Neubig, G. (2017). A syntactic neural model for general-purpose code generation. ACL, 440-450.
Zhou, Z., Zou, D., Zhang, L., Sun, J., & Hassan, A. E. (2020). Code security analysis with machine learning: Challenges and opportunities. IEEE Software, 37(2), 67-75.
Rozière, B., Lachaux, M. A., Chanussot, L., & Lample, G. (2020). Unsupervised translation of programming languages. Advances in Neural Information Processing Systems, 33, 20601–20611.
Wang, Y., Dong, H., Yu, D., & Wang, H. (2021). Bridging symbolic and neural approaches for code generation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 13066–13074.
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.