Automated source code summarization via transformer
Source code summarization is a comprehensible description of a program’s functionality. The code summarization assists developers to understand large portions of source code, thus reducing the time taken to comprehend a program’s capabilities. To automate the code summarization, programs have used R...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/153188 |
| _version_ | 1826121403468873728 |
|---|---|
| author | Viswen Kumar Mariammalle |
| author2 | Liu Yang |
| author_facet | Liu Yang Viswen Kumar Mariammalle |
| author_sort | Viswen Kumar Mariammalle |
| collection | NTU |
| description | Source code summarization is a comprehensible description of a program’s functionality. The code summarization assists developers to understand large portions of source code, thus reducing the time taken to comprehend a program’s capabilities. To automate the code summarization, programs have used RNN-based neural architecture to create neural network models for this natural language translation. However, the RNN-based neural architecture has two particular limitations which are its disability to process the non-sequential structure of the source codes and missing out on the long-term relationships between code tokens. My proposed approach of using Transformer neural architecture is able to overcome these limitations. Compared against the RNN-based neural network models, the Transformer network model has shown significantly better experimental results of BLEU 1, 2, 3 and 4 scores, ranging between three to seven scores higher, METEOR score of three higher and ROUGE-L score of one higher. |
| first_indexed | 2024-10-01T05:32:04Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/153188 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:32:04Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1531882021-11-16T05:09:40Z Automated source code summarization via transformer Viswen Kumar Mariammalle Liu Yang School of Computer Science and Engineering yangliu@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Document and text processing Source code summarization is a comprehensible description of a program’s functionality. The code summarization assists developers to understand large portions of source code, thus reducing the time taken to comprehend a program’s capabilities. To automate the code summarization, programs have used RNN-based neural architecture to create neural network models for this natural language translation. However, the RNN-based neural architecture has two particular limitations which are its disability to process the non-sequential structure of the source codes and missing out on the long-term relationships between code tokens. My proposed approach of using Transformer neural architecture is able to overcome these limitations. Compared against the RNN-based neural network models, the Transformer network model has shown significantly better experimental results of BLEU 1, 2, 3 and 4 scores, ranging between three to seven scores higher, METEOR score of three higher and ROUGE-L score of one higher. Bachelor of Engineering (Computer Science) 2021-11-16T01:11:53Z 2021-11-16T01:11:53Z 2021 Final Year Project (FYP) Viswen Kumar Mariammalle (2021). Automated source code summarization via transformer. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153188 https://hdl.handle.net/10356/153188 en SCSE20-0713 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Document and text processing Viswen Kumar Mariammalle Automated source code summarization via transformer |
| title | Automated source code summarization via transformer |
| title_full | Automated source code summarization via transformer |
| title_fullStr | Automated source code summarization via transformer |
| title_full_unstemmed | Automated source code summarization via transformer |
| title_short | Automated source code summarization via transformer |
| title_sort | automated source code summarization via transformer |
| topic | Engineering::Computer science and engineering::Computing methodologies::Document and text processing |
| url | https://hdl.handle.net/10356/153188 |
| work_keys_str_mv | AT viswenkumarmariammalle automatedsourcecodesummarizationviatransformer |