Thursday, May 26, 2022 - 15:00 to 17:00
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science is pleased to present…
MSc Thesis Proposal by: Malita Dodti
Date: Thursday May 26th, 2022
Time: 3:00pm - 5:00 pm
Meeting URL: https://us06web.zoom.us/j/85452661743?from=addon
Passcode: If interested in attending this event, contact the Graduate Secretary at email@example.com with sufficient notice before the event to obtain the passcode.
Question Answering (QA) is a complex Natural Language Processing (NLP) task. It involves understanding a question, retrieving relevant materials, and generating a suitable answer. Its major challenge is to create proper representations of the language and to produce a suitable answer to a given question. Pretraining neural language models have significantly improved many natural language processing tasks. In particular, BERT is a deeply bidirectional, pre-trained language representation that has performed well in NLP tasks including question answering. In this thesis work, we study the application of the BERT technique to automated response generation for biomedical text mining. This application comes from the consideration that, due to the growth of the volume of biomedical papers, biomedical text mining is demanding better techniques to automate the extraction and the summarization of the biomedical information and to automate the responses to the queries. We apply a fine-tuning technique developed for the language representation obtained from the general domain to some domain-specific data using the transfer learning technique. Addressing domain-specific context allows for further advancement in performing the language-related tasks. For example, with the information in the biomedicine, which contains a large amount of unlabelled text, a domain-specific pre-trained model can be shown to outperform the general language models. The proposed work is expected to improve the effectiveness of the state-of-the-art techniques for performing question answering tasks in the context of biomedical text mining.
Keywords: Question Answering, Natural Language Processing, BERT (Bidirectional Encoder Representations from Transformers), Pre-training, Fine-tuning technique, Domain-specific model, Language representation, Text mining.
MSc Thesis Committee:
Internal Reader: Dr. Luis Rueda
External Reader: Dr. Huiming Zhang (Department of Biomedical Sciences)
Advisor: Dr. Jessica Chen
MSc Thesis Proposal Announcement
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 firstname.lastname@example.org