Tools
Tools
Hanif, Usama (2023) Research Paper Summarization Using Text-To-Text Transfer Transformer (T5) Model. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
There is a massive amount of research papers available online, and they keep increasing quickly but reading and understanding the sense of these long papers takes up a lot of time. This is where AI can lend a hand as it can help people understand these papers faster and pull out important information to create shorter summaries. In this study, the main focus was on a specific AI model called the Text-to-Text Transfer Transformer (T5) model. It was trained using a bunch of research papers and their summaries written by experts. The T5 model was fine-tuned so that it can become good at making brief yet meaningful summaries of these research papers. To evaluate the performance of the proposed approach, some measures like ROUGE and BLEU were used. This proposed approach scored well: it got 83% for ROUGE-1, 82% for ROUGE-2, 83% for ROUGE-3, and 47% for BLEU. These scores show how accurate and effective the approach is in summarizing the papers. The T5 model was also compared with other advanced models like BERT, GPT-2, and BART. The T5 model's summaries turned out to be more accurate in comparison. This study demonstrates that AI, especially the T5 model, can be a useful tool for quickly understanding complex research papers and creating helpful summaries. This could make it much easier for researchers and readers to get the main points from a lot of research without spending too much time.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Rustam, Furqan UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Research Z Bibliography. Library Science. Information Resources > ZA Information resources > Research |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 22 Nov 2024 11:47 |
| Last Modified: | 22 Nov 2024 11:47 |
| URI: | https://norma.ncirl.ie/id/eprint/7190 |
Actions (login required)
 |
View Item |