Extractive Text Summarization of News Reports Leveraging Transfer Learning Contextual Embedders

Karkada, Savin Vishwas (2022) Extractive Text Summarization of News Reports Leveraging Transfer Learning Contextual Embedders. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The Surge in textual data has been on an all time high in the recent past in a variety of forms both physically and digitally. One of the leading sources for these data points are the news data which hold enormous potential insights that can transform business operations.One of the key tasks extractive text summarization to provide consumption friendly news reports. The following study investigates the use of contextual embedders to semantically capture the meaning while effectively summarizing the news reports. The contextual embedders have been utilized to perform the task of word embedding while K-Means clustering has been implemented to generate summary out of the embeddings. The pre-trained models BERT, RoBERTa, ELMo and Word2Vec are used to compare the effectiveness and the influence they have on summarization through contextual embedding is studied and measured statistically using ROUGE scores.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HM Sociology > Information Science > Communication 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:	20 Feb 2023 15:46
Last Modified:	02 Mar 2023 09:51
URI:	https://norma.ncirl.ie/id/eprint/6199

Actions (login required)

View Item