Text Documents Classification in Uzbek Language
O Babomuradov OzodScientific and Innovation Center of Information and Communication Technologies at TUIT named after Al-Kharezmi, Tashkent, Uzbekistan B.Otaxonova4,Narzillo MamatovScientific and Innovation Center of Information and Communication Technologies at TUIT named after Al-Kharezmi, Tashkent, UzbekistanL Kadrkhuja Djuraxodjaevich BoboevTashkent universityR MadsenS SigurdssonL HansenJ LarsenJ PaikS KimK HanH RimS MyaengY YimingJ ThorstenP PhilippW BonnieB HarishD GuruS ManjunathN KamalK AndrewT SebastianM TomI PolyakovT SokolovaA ChepovskiiA Chepovsky
ABI
Аннотация
This article deals with intellectual analyzing technologies, which classify texts in Uzbek language, in which the Bernoulli and multi-nominal models are considered. The textual documents used in this research are from the authentic sources of The State National Information Agency of Uzbekistan. To compare the probability methods of classification, 600 documents of 6 types of categories, with 169205 words, have been used.
Перевод пока недоступен