Transformer based model for News Headline Generation task by incorporating Named Entity Recognition

Veientlena, Steffi (2023) Transformer based model for News Headline Generation task by incorporating Named Entity Recognition. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Business these days are looking for insights from large amount of data from various sources for strategic growth. Textual information, specially news data has seen notable upsurge in the past years. This necessities the effective method to manage and comprehend the abundance of textual content. In order to meet this challenge, Extraction and Abstractive text summarization techniques can be used which allows more streamlined information management and consumption. This research study suggests the novel use of abstractive summarization on news data with a purpose of producing news headline that are appropriate to the context. while the earlier studies focused on attention based models for abstractive text summarization. This study goes further by examining the integration of named entity recognition (NER) with transformer based T5 model, renowned for its efficacy in language understanding and text generation task.The ROUGE and Bert score evaluation metric commonly used evaluate the quality of generated text in comparison with the actual text has been used in this study to examine the robustness of the proposed model.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nayak, Prashanth 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
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	08 Jan 2025 17:24
Last Modified:	08 Jan 2025 17:24
URI:	https://norma.ncirl.ie/id/eprint/7286

Actions (login required)

View Item