Keyword Extraction in Persian Text Documents Using Semantic Analysis
Keyword Extraction in Persian Text Documents Using Semantic Analysis
Hadi Veisi1 Niloofar Aflaki2
1) University of Tehran Faculty of new Sciences and Technologies,Email:
2) University of Tehran Kish International Campus, Email:
IOI Code
:
XYCZ-AADCA
Publication :
International Conference on Engineering and Applied Science(iceasconf.com)
Abstract :
All texts and documents are written to develop a theory, innovation or public notice and each one has its own unique idea. These documents can be summarized in a series of words that we call them keywords. By studying this set of words during the searching process, the goals were realized and if it was appropriate to the subject of the searching, read the entire document. Keywords are considered as the most important words and phrases in a text that can show fundamental idea of a text in the form of short and summarized words.
In this article keyword extraction in Persian text using semantic analysis examined. That considered set of Persian-language news sites with their predefined keywords. Then extract their keywords by using Lesk algorithm, which is a comparison algorithm. After that compared extracted words with predefined keywords with precision and recall and compared the results of precision and recall with the frequency method, which is one of the most common methods for extracting keywords.
Keywords : semantic analysis semantic similarity persian text