Thesaurus-aided learning for rule-based categorization of Ocr texts

The question posed in this thesis is whether the effectiveness of the rule-based approach to automatic text categorization on OCR collections can be improved by using domain-specific thesauri. A rule-based categorizer was constructed consisting of a C++ program called C-KANT which consults documents and creates a program which can be executed by the CLIPS expert system shell. A series of tests using domain-specific thesauri revealed that a query expansion approach to rule-based automatic text categorization using domain-dependent thesauri will not improve the categorization of OCR texts. Although some improvement to categorization could be made using rules over a mixture of thesauri, the improvements were not significantly large.

Name thesis:degree_name

Master of Science (MS)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor dc:publisher

University of Nevada, Las Vegas

Year

2003

Author dc:creator

• Coombs, Jeffrey Scott

Contributors dc:contributor

• Kazem Tagva

Statement dc:rights

• IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Language dc:language

English

Identifier

https://oasis.library.unlv.edu/rtds/1614

OAI identifier oai:identifier

oai:oasis.library.unlv.edu:rtds-2613