NORMA eResearch @NCI Library

To what extent NLP with RNN and Transformer Based Deep Neural Network can be used to classify Insincere questions on Quora

Shrivas, Rohit Kumar (2021) To what extent NLP with RNN and Transformer Based Deep Neural Network can be used to classify Insincere questions on Quora. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This research project adopts a novel approach of utilizing BERT based models for question classification application of NLP. The performance of these models are then evaluated using F1 score and compared with the performance of RNN based Deep Learning models with and without Attention layer. The DistilBERT model outperformed every model implemented in the research and achieved an F1 score of 94.87% which is 7.06% improvement over previous studies. Among the RNN based Deep Learning models, Model-6 (Bi-directional GRU + Bi-directional LSTM + Attention layer) performed the best and achieved an F1 score of 63.53%.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 14 Dec 2021 13:42
Last Modified: 14 Dec 2021 13:42
URI: http://norma.ncirl.ie/id/eprint/5221

Actions (login required)

View Item View Item