hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.31341/jios.44.1.8

Analysis of Text Collections for the Purposes of Keyword Extraction Task

Alexander Vanyushkin ; Pskov State University, Pskov, Russia
Leonid Graschenko ; Institute of Mathematics named A. Juraev of the Academy of Sciences of the Republic of Tajikistan, Dushanbe, Tajikistan

Puni tekst: engleski, pdf (2 MB) str. 171-184 preuzimanja: 36* citiraj
APA 6th Edition
Vanyushkin, A. i Graschenko, L. (2020). Analysis of Text Collections for the Purposes of Keyword Extraction Task. Journal of Information and Organizational Sciences, 44 (1), 171-184. https://doi.org/10.31341/jios.44.1.8
MLA 8th Edition
Vanyushkin, Alexander i Leonid Graschenko. "Analysis of Text Collections for the Purposes of Keyword Extraction Task." Journal of Information and Organizational Sciences, vol. 44, br. 1, 2020, str. 171-184. https://doi.org/10.31341/jios.44.1.8. Citirano 20.09.2020.
Chicago 17th Edition
Vanyushkin, Alexander i Leonid Graschenko. "Analysis of Text Collections for the Purposes of Keyword Extraction Task." Journal of Information and Organizational Sciences 44, br. 1 (2020): 171-184. https://doi.org/10.31341/jios.44.1.8
Harvard
Vanyushkin, A., i Graschenko, L. (2020). 'Analysis of Text Collections for the Purposes of Keyword Extraction Task', Journal of Information and Organizational Sciences, 44(1), str. 171-184. https://doi.org/10.31341/jios.44.1.8
Vancouver
Vanyushkin A, Graschenko L. Analysis of Text Collections for the Purposes of Keyword Extraction Task. Journal of Information and Organizational Sciences [Internet]. 2020 [pristupljeno 20.09.2020.];44(1):171-184. https://doi.org/10.31341/jios.44.1.8
IEEE
A. Vanyushkin i L. Graschenko, "Analysis of Text Collections for the Purposes of Keyword Extraction Task", Journal of Information and Organizational Sciences, vol.44, br. 1, str. 171-184, 2020. [Online]. https://doi.org/10.31341/jios.44.1.8

Sažetak
The article discusses the evaluation of automatic keyword extraction algorithms (AKEA) and points out AKEA’s dependence on the properties of the test collection for effectiveness. As a result, it is difficult to compare different algorithms who’s tests were based on various test datasets. It is also difficult to predict the effectiveness of different systems for solving real-world problems of natural language processing (NLP). We take in to consideration a number of characteristics, such as the text length distribution in words and the method of keyword assignment. Our analysis of publicly available analytical exposition text which is typical for the keywords extraction domain revealed that their length distributions are very regular and described by the lognormal form. Moreover, most of the article lengths range between 400 and 2500 words. Additionally, the paper presents a brief review of eleven corpora that have been used to evaluate AKEA’s.

Ključne riječi
text corpus; corpus linguistics; keyword extraction; text length distribution; natural language processing; information retrieval

Hrčak ID: 239794

URI
https://hrcak.srce.hr/239794

Posjeta: 65 *