Tools
Tools
Gupta, Gaurav (2024) Enhancing the Accuracy of Abstractive and Extractive Summarization of Patient Discharge Reports by using Transfer models. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
We will conduct our research on extractive and abstractive text summarization in the medical field. The accuracy of medical report summaries has been fairly limited up until now, but since it will save doctors and patients time, it is time for improvements. The National Institutes of Health states that it takes 60 hours on average to handle a patient’s discharge report and also the ratio of doctors to patients in developing and poor nations is approximately 0.05 %. Sentence-to-sentence models and encode-decoders have been the focus of much previous research on this problem, but more recent work has shown that abstractive summarization techniques like T5, DistilBART, and Pegasus, as well as extractive summarization techniques like BERTSUM and XLNet, can produce better results. Analyze the generated text by ROUGE and BERT score and evaluate on the basis of relevance, coherence, and fluency of the generated text.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email -, - 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 R Medicine > Healthcare Industry |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 18 Aug 2025 15:25 |
| Last Modified: | 18 Aug 2025 15:25 |
| URI: | https://norma.ncirl.ie/id/eprint/8572 |
Actions (login required)
 |
View Item |