BNIE 3.0 (Business news information extraction 3.0)

Date of Publication

2011

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

Subject Categories

Computer Sciences

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Nathalie Rose Lim-Cheng

Defense Panel Chair

Ethel Ong

Defense Panel Member

Shirley Chu

Allan Borra

Abstract/Summary

Information Extraction (IE) locates and retrieves structured information from unstructured text. Such technology is useful for Business Intelligence (BI), which is the analysis of business data with the help of computers. The research involved the design and implementation of a system that extracts information on business transactions between two or more companies from business news articles and stores these into a database for a more structured view to facilitate comparisons of data. The proponents tested BNIE 3.0 on 75 business news articles form BioSpace.com, and the system was able to achieve an F-measure of 70.28%. With the addition of typed dependencies in semantic interpretation, it has a higher accuracy compared with the 56.27% F-measure of BNIE 2.0 tested on the same 75 business news articles.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU18563

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1v. various foliations : illustrations (some colored) ; 28 cm.

Keywords

Text processing (Computer science); Natural language processing (Computer science)

This document is currently not available here.

Share

COinS