Thursday, December 15, 2022 - 13:00 to 14:30
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science is pleased to present…
MSc Thesis Proposal by: Mrulay Mistry
Date: Thursday December 15, 2022
Time: 1:00 pm – 2:30 pm
Location: Essex Hall, Room 105
Reminders: Two-part attendance is mandatory, arrive 5-10 minutes prior to the event starting - LATECOMERS WILL NOT BE ADMITTED once the door has been closed and the presentation has begun. Please be respectful of the presenter by NOT knocking on the door for admittance.
In the domain of Natural Language Processing (NLP), the representation of words according to their distribution in the vector form is the most crucial task. When the words are represented in a way where similar words are placed close by on a plane of words, better results are achieved in any NLP task. The methods used previously have been putting emphasis on words appearing near each other and passing the word tokens through a Neural Language model to capture the context of the words, but these methods have not been able to achieve high scores in the problem of word similarity. This paper introduces a method to represent the words in the form of a graph in such a way that their first-order and second-order proximity is preserved. We then subject the generated graph to a vertex embedding method to generate their embedding. After experimenting with the proposed method on multiple text corpora, our findings indicate that this method of word representation outperforms the traditional word-embedding methods by more than 10% in the task of not only word similarity but also text classification and question answering.
Keywords: Word Embedding, Graph Representation, Graph Embedding, AutoEncoders
MSc Thesis Committee:
Internal Reader: Dr. Hossein Fani
External Reader: Dr. Reza Nakhaie
Advisor: Dr. Ziad Kobti
MSc Thesis Proposal Announcement
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 email@example.com