Using Machine Learning to Improve Rule based Arabic Named Entity Recognition

DISSERTATION WITH DISTINCTION

Saved in:
Bibliographic Details
Main Author: Shoaib, Muhammad (author)
Published: 2011
Subjects:
Online Access:http://bspace.buid.ac.ae/handle/1234/58
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1862980618535567360
author Shoaib, Muhammad
author_facet Shoaib, Muhammad
author_role author
dc.creator.none.fl_str_mv Shoaib, Muhammad
dc.date.none.fl_str_mv 2011-01
2013-03-21T14:21:09Z
2013-03-21T14:21:09Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv 90049
http://bspace.buid.ac.ae/handle/1234/58
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv The British University in Dubai (BUiD)
dc.subject.none.fl_str_mv information extraction
named entity recognition
machine learning
named entity annotation
dc.title.none.fl_str_mv Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
dc.type.none.fl_str_mv Dissertation
description DISSERTATION WITH DISTINCTION
id budr_4fece1b21116ea96508bc6fa2dcc7bc4
identifier_str_mv 90049
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/58
publishDate 2011
publisher.none.fl_str_mv The British University in Dubai (BUiD)
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Using Machine Learning to Improve Rule based Arabic Named Entity RecognitionShoaib, Muhammadinformation extractionnamed entity recognitionmachine learningnamed entity annotationDISSERTATION WITH DISTINCTIONArabic Language is widely spoken and highly influential Language both politically and geographically. Thus it is crucial to perform Information Extraction on diverse Arabic texts. In past decade many researchers have targeted the Information Extraction in general and Named Entity Recognition in particular for Arabic language. Mostly researchers have applied Machine Learning for Arabic Named Entity Recognition while few researchers have used hand crafted rules for Named Entity Recognition task.The Machine Learning techniques and rule based techniques for named entity recognition are mostly viewed as rival approaches. The work presented in this thesis is an effort to combine rule based and Machine Learning approaches into a Hybrid System for Named Entity Recognition. The Person, Organization and Location entities identified by rule based system are used as features combined with several other features for Machine Learning system. The final outcome provides enhanced Named Entity annotations.The evaluation of the experiments conducted shows that the Hybrid approach stated in thesis significantly improves the quality of named entity recognition of independent rule based system and independent Machine Learning system. Moreover the statistical significance tests confirms that the results obtained are valid and not occurred by chance.The British University in Dubai (BUiD)2013-03-21T14:21:09Z2013-03-21T14:21:09Z2011-01Dissertationapplication/pdf90049http://bspace.buid.ac.ae/handle/1234/58enoai:bspace.buid.ac.ae:1234/582021-10-17T11:29:24Z
spellingShingle Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
Shoaib, Muhammad
information extraction
named entity recognition
machine learning
named entity annotation
title Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
title_full Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
title_fullStr Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
title_full_unstemmed Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
title_short Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
title_sort Using Machine Learning to Improve Rule based Arabic Named Entity Recognition
topic information extraction
named entity recognition
machine learning
named entity annotation
url http://bspace.buid.ac.ae/handle/1234/58