Specialization of keyword extraction approach to Persian texts

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.

PAKE: a supervised approach for Persian automatic keyword extraction using statistical features

“…In their proposed method, the statistical characteristics for the different words are calculated and the probable keywords are selected using fuzzy rules. Khozani and Bayat [15] have used statistical methods. The proposed method consists of two steps.…”

Persian Keyphrase Generation Using Sequence-to-Sequence Models

“…Khozani and Bayat [23], after stemming and removing stop words, uses TFIDF (Term Frequency times Inverse Document Frequency) to calculate the weights of the words in the documents. After calculating the weights of the tokens, the weights of the bi-token keyphrases are calculated using a cooccurrence matrix.…”