Improving Keyword Extraction in Multilingual Texts

  • نویسندگان: مجید عبدالرزاق نژاد, بهاره هاشم زاده
  • کلمات کلیدی: Text mining; Data retrieval; Keyword extraction; Language independent; TF-IDF algorithm; Graph-based algorithm

The accuracy of keyword extraction is a leading factor in marketing and information management. In the present study, the available information of all languages is used simultaneously to improve keyword extraction in a multilingual text, such that a word is selected as the keyword of a text in a certain language that in addition to that language holds a high rank based on the keywords criteria in other languages, as well. Thus, that a word has the keyword criteria only in one language not in other languages may not qualify it as a keyword. This could decrease the percentage of false keywords and increase the accuracy of an algorithm. The obtained results indicated that algorithm accuracy of the multilingual texts in term frequency- inverse document frequency (TF-IDF) algorithm, graph-based algorithm, and the improved proposed algorithm is 80%, 60.65%, and 91.3%, respectively.

پیوند مجله / همایش

نرم افزار همراه دانشگاه بزرگمهر

مشاهده ی اخبار و ارائه خدمات آموزشی، دانشجوئی و رفاهی به دانشجویان و اساتید دانشگاه بزرگمهر قائنات از طریق نرم افزار تلفن همراه