DocumentCode
2774047
Title
Stemmer Algorithm for Arabic Words Based on Excessive Letter Locations
Author
Al-Shalabi, Riyad ; Kanaan, Ghassan ; Ghwanmeh, Sameh ; Nour, Fuad Mousa
Author_Institution
Arab Acad. for Banking & Financial Sci., Amman
fYear
2007
fDate
18-20 Nov. 2007
Firstpage
456
Lastpage
460
Abstract
The paper describes a new stemmer algorithm to find the roots and patterns for Arabic words based on excessive letter locations. The algorithm locates the trilateral root , quadri-literal root as well as the pentaliteral root. The algorithm is written with the goal of supporting natural language processing programs such as parsers and information retrieval systems. The algorithm has been tested on thousands of Arabic words. Results reveals an accuracy reached to 95%.
Keywords
natural language processing; Arabic words; information retrieval systems; natural language processing; parsers; pentaliteral root; quadri-literal root; stemmer algorithm; trilateral root; Banking; Books; Information retrieval; Natural language processing; Natural languages; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Innovations in Information Technology, 2007. IIT '07. 4th International Conference on
Conference_Location
Dubai
Print_ISBN
978-1-4244-1840-4
Electronic_ISBN
978-1-4244-1841-1
Type
conf
DOI
10.1109/IIT.2007.4430444
Filename
4430444
Link To Document