The University of Windsor is preparing for a safe return to campus. Learn More.

PhD Dissertation Proposal by Ala Alam Falaki:"Generic Abstractive Text Summarization using Deep Neural Networks and Pretrained Models "

Friday, October 23, 2020 - 13:00 to 14:30

The School of Computer Science is pleased to present… 

PhD Dissertation Proposal by: Ala Alam Falaki 

 
Date: Friday, October 23, 2020 
Time:  1:00 PM – 2:30pm 
 

Abstract:  

Recent advances in Natural Language Processing (NLP) field follows a trend of training gigantic models to achieve the state-of-the-art result, especially after the introduction of the Transformer architecture. ProphNet, PEGASUS, and GPT-3 are a few examples of these large models which either inherit whole or parts of the Transformer architecture. There is no doubt that these models perform well, but the cost of training and maintaining them is a real issue. Also, processing long sequences is still a challenge and will be achievable by adding even more parameters as the number of parameters grows quadratically with the size of the input. We are doing experiments on the sequence-to-sequence models to get similar performance with fewer parameters. We already obtained better results than the GPT-2 model with less than 90% of the original model’s total number of parameters in the text summarization task. Even though the results are not close to state-of-the-art, it shows that there is room for improvement. 
 
Keywords: Natural Language Processing, Text Summarization, Abstractive 
 

Thesis Committee:  

Internal Reader: Dr. Luis Rueda 
Internal Reader:  Dr. Dan Wu 
External Reader: Dr. Jonathan Wu 
External Examiner: TBD  
Advisor: Dr. Robin Gras 
 
 

PhD Dissertation Proposal Announcement   Vector Institute Artificial Intelligence approved logo

 

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca