Semantic Enhancement for Text Representation

Hou, Wenfeng

Semantic Enhancement for Text Representation

Hou, Wenfeng

Permalink

Publication Type:: Thesis
Issue Date:: 2021

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (142.07 kB)

Adobe PDF

Download thesisAdobe PDF (1.14 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Hou, Wenfeng
dc.date.accessioned	2022-01-10T00:56:14Z
dc.date.available	2022-01-10T00:56:14Z
dc.date.issued	2021
dc.identifier.uri	http://hdl.handle.net/10453/152857
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	With the development of web technology, various information can be found online in the form of text such as social media, news description, product review, and instant message. Text classification is a traditional task in natural language processing. Learning useful text representations has attracted much attention in machine learning. Traditional implicit representation models can capture richer information from context with the help of deep neural networks. However, those methods fail to capture the explicit semantic information. In order to enhance the text representation, we focus on introducing external knowledge to the semantic enhancement for text representation. First we will propose a deep Entity-based Concept Knowledge-Aware (ECKA) representation model which incorporates semantic information into short text representation. Second, we will propose an explicit semantic-based term weighting scheme to improve the term weighting. Experiment results demonstrate the efficiency and effectiveness of our proposed models.	en_US.UTF-8
dc.format	Thesis (MAnalytics)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/152857/2/02whole.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	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.rights	au.edu.uts.lib/ppc
dc.title	Semantic Enhancement for Text Representation	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

With the development of web technology, various information can be found online in the form of text such as social media, news description, product review, and instant message. Text classification is a traditional task in natural language processing. Learning useful text representations has attracted much attention in machine learning. Traditional implicit representation models can capture richer information from context with the help of deep neural networks. However, those methods fail to capture the explicit semantic information. In order to enhance the text representation, we focus on introducing external knowledge to the semantic enhancement for text representation. First we will propose a deep Entity-based Concept Knowledge-Aware (ECKA) representation model which incorporates semantic information into short text representation. Second, we will propose an explicit semantic-based term weighting scheme to improve the term weighting. Experiment results demonstrate the efficiency and effectiveness of our proposed models.

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

http://hdl.handle.net/10453/152857