|
Makerere University Research Repository >
Faculty of Computing and Information Technology >
Conference and Workshop Reports (CIT) >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/123456789/1979
|
| Title: | A methodology for feature selection in named entity recognition |
| Authors: | Kitoogo, Fredrick Edward
Baryamureeba, Venansius |
| Keywords: | named entity recognition
multiobjective genetic algorithm
machine learning algorithm |
| Issue Date: | 2007 |
| Publisher: | Fountain Publishers Kampala |
| Citation: | Kitoogo, F. E. and Baryamureeba, V. (2007, Augus 5-8). A methodology for feature selection in named entity recognition. 3rd Annual International Conference on Computing and ICT Research: Computer Science, pp.88-100 |
| Series/Report no.: | SREC
07 |
| Abstract: | In this paper a methodology for feature selection in named entity recognition is
proposed. Unlike traditional named entity recognition approaches which mainly
consider accuracy improvement as the sole objective, the innovation here is manifested
in the use of a multiobjective genetic algorithm which is employed for feature
selection basing on various aspects including error rate reduction and time taken
for evaluation, and also demonstrating the use of Pareto optimization. The proposed
method is evaluated in the context of named entity recognition, using three different
data sets and a K-nearest Neighbour machine learning algorithm. Comprehensive
experiments demonstrate the feasibility of the methodology. |
| Description: | Conference paper which can be dowloaded in fulltext from the conference organiser's website at the URL link above |
| URI: | http://cit.mak.ac.ug/iccir/downloads/SREC_07/Fredrick%20Edward%20Kitoogo%20and%20Venansius%20Baryamureeba_07.pdf
http://hdl.handle.net/123456789/1979 |
| ISBN: | 978-9970-02-730-9 |
| Appears in Collections: | Conference and Workshop Reports (CIT)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| kitoogo-fredrick-edward-and-baryamureeba-venansius-cit-conf.pdf | | 355Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
