Tools
Tools
Belur Ramesh, Pramod (2022) Automated Code Summarization of Program Subroutines Using Deep Learning Technologies. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (976kB) | Preview |
Preview |
PDF (Configuration manual)
Download (991kB) | Preview |
Abstract
Software Engineering field, now, is enjoying a burst of data-driven research as there is an interest in code generation, code optimization, code summarization, code understanding etc. Automated source code summarization is generating succint source code summaries without human intervention by learning code sequences. Automated way of generating source code summaries by leveraging data and deep learning techniques to reduce the burden on programmers and bring about faster and better knowledge management in the software engineering industry is purpose of this reaseach. The approach of building models that understand programming languages and summarizes them in English has far-reaching impacts which will bring about democratizing programming to even non-programmers.
In our approach source code of 2.1 million java code-comment pairs was used to train deep learning models to generate summaries, traditional encoder-decoder models were conflated with Graph Neural Network (GNN) and its impact was measured against a model with a traditional sequence to sequence model. The GNN model outperformed the sequence to sequence in all the evaluation metrics of BLEU and ROUGE by at least 1%, which means that the overlap between a human-written reference summary and a model generated summary is more with GNN than without GNN.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 18 Jan 2023 16:51 |
| Last Modified: | 06 Mar 2023 16:56 |
| URI: | https://norma.ncirl.ie/id/eprint/6084 |
Actions (login required)
 |
View Item |