Title :
Specialization of keyword extraction approach to Persian texts
Author :
Khozani, Sayyid Mohammad Hoseini ; Bayat, Hosein
Author_Institution :
Dept. of Comput. Sci., Islamic Azad Univ., Tafresh, Iran
Abstract :
As the amount of data increases and the relations among them get more complex, access to information implicit in data appears more difficult, and the role of methods of getting data from diverse texts, and analyzing them becomes more significant. Of such methods is the highly effective technique of keyword extraction which shows the concept and content of the original text. In this article, a new approach is presented with the aim of extracting keywords with respect to combined words, and extracting key sentences in Persian documents so as to classify them efficiently. Studies performed on several Persian documents, and comparisons done between the findings of these and other methods have proven that this method extracts keywords of texts with much more accuracy and speed to represent the original concepts.
Keywords :
document handling; pattern classification; text analysis; word processing; Persian document classification; Persian text; keyword extraction; word extraction; Classification algorithms; Computers; Data mining; Educational institutions; Feature extraction; Vectors; Persian documents; classification; content; extraction; keywords;
Conference_Titel :
Soft Computing and Pattern Recognition (SoCPaR), 2011 International Conference of
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-1195-4
DOI :
10.1109/SoCPaR.2011.6089124