Tools
Tools
Mukherjee, Aditya (2022) Developing Bengali Text Summarization with Transformer Base model. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
For high-resource languages like English and other European languages, text summarization using deep learning has become a well-studied research subject. However, for poorly available resource languages such as Indian subcontinent languages and African languages, relatively few efforts have been done on the Internet. Due to a lack of a sufficient parallel corpus, parser, tokenizer, POS taggers, and other tools, resource-constrained languages have a restricted reach in natural language processing (NLP). We propose an abstractive text summarization sequence for a deep learning model for Bengali in this Research study. This Research study adopt a novel approach towards Summarizing the Bengali text which have been collected from Bangla news corpus and try to implement the LSTM-RNN based Encoder and decoder model with attention mechanism and Transformer based model called multilingual- T5 model and will Evaluate their result with each other using ROUGE metric. In this study we will be using many NLP tools too, to process the data and will clean it before inputting the data into our model.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | P Language and Literature > PK Indo-Iranian 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) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 23 Feb 2023 13:46 |
| Last Modified: | 02 Mar 2023 08:48 |
| URI: | https://norma.ncirl.ie/id/eprint/6232 |
Actions (login required)
 |
View Item |