Rules frequency order stemmer for Malay language.

The importance of stemmer is obvious with the advent of effective information retrieval systems. Unfortunately, Malay stemming problems are difficult to solve due to complexity of words morphology. The Rules Application Order (RAO)stemmer is examined for enhancing performance to minimize the percen...

Celý popis

Podrobná bibliografie
Hlavní autoři: Abdullah, Muhammad Taufik, Ahmad, Fatimah, Mahmod, Ramlan, Tengku Sembok, Tengku Mohd
Médium: Článek
Jazyk:English
English
Vydáno: International Journal of Computer Science and Network Security (IJCSNS) 2009
On-line přístup:http://psasir.upm.edu.my/id/eprint/17738/1/Rules%20frequency%20order%20stemmer%20for%20Malay%20language.pdf
Popis
Shrnutí:The importance of stemmer is obvious with the advent of effective information retrieval systems. Unfortunately, Malay stemming problems are difficult to solve due to complexity of words morphology. The Rules Application Order (RAO)stemmer is examined for enhancing performance to minimize the percentage of stemming errors. This paper presents a stemming approach called Rules Frequency Order (RFO). RFO rearranges the stemming rules according to the frequency of their usage from the previous execution. It shows that the approach provides a higher percentage of stemming correctness as compared to RAO stemming approach.