Towards Robust and Interpretable Logical Reasoning in Machine Reading Comprehension

Huang, Hao

Towards Robust and Interpretable Logical Reasoning in Machine Reading Comprehension

Huang, Hao

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (2.64 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.advisor	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.contributor.advisor	© 2023 Hao Huang
dc.contributor.advisor	au.edu.uts.lib/cph
dc.contributor.author	Huang, Hao
dc.date.accessioned	2024-06-12T05:11:18Z
dc.date.available	2024-06-12T05:11:18Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/179489
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Natural Language Processing (NLP) has made significant strides using large pretrained language models in recent years. However, Natural Language Understanding (NLU) necessitates more profound understanding and reasoning capabilities that traditional NLP methods struggle to provide. This thesis concentrates on four aspects of augmentation of machine reading comprehension models: knowledge graph completion, procedural text understanding, temporal order extraction, and autodebiasing. Collectively, these components contribute to robust and interpretable logical reasoning in machine reading comprehension step by step.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/179489/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Towards Robust and Interpretable Logical Reasoning in Machine Reading Comprehension	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Natural Language Processing (NLP) has made significant strides using large pretrained language models in recent years. However, Natural Language Understanding (NLU) necessitates more profound understanding and reasoning capabilities that traditional NLP methods struggle to provide. This thesis concentrates on four aspects of augmentation of machine reading comprehension models: knowledge graph completion, procedural text understanding, temporal order extraction, and autodebiasing. Collectively, these components contribute to robust and interpretable logical reasoning in machine reading comprehension step by step.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/179489