The Problem OF Words Undergoing Sound Changes in Uzbek Stemmers
B. (Botir) ElovDoctor of philosophy of technical sciences (PhD) , associate professor Tashkent State University of Uzbek Language Tashkent State University of Uzbek Language Master of degree , Alisher Navo9i Tashkent State University of Uzbek Language and LiteratureZ. (Zilola) XusainovaDoctor of philosophy of technical sciences (PhD) , associate professor Tashkent State University of Uzbek Language Tashkent State University of Uzbek Language Master of degree , Alisher Navo9i Tashkent State University of Uzbek Language and LiteratureH. (Habiba) BerdiyevaDoctor of philosophy of technical sciences (PhD) , associate professor Tashkent State University of Uzbek Language Tashkent State University of Uzbek Language Master of degree , Alisher Navo9i Tashkent State University of Uzbek Language and Literature
ABI
Annotatsiya
Stemming is one of the most common initial data processing steps that can be performed on almost all Natural Language Processing (NLP) projects. In the process of Stemming, it is carried out to remove some part of the word or shorten the word to its root. Several stemming algorithms are used to decide how to cut a word. In determining the stem of Uzbek words, problems such as homonymy of root and suffix with one root, sound changes when the suffix is added to the words, stemming of neologisms and NERs can occur. This article presents models for solving the problem of the occurrence of sound changes in words in the process of performing stemming in the texts of the Uzbek language Corpus.
Hali tarjima qilinmagan
Iqtiboslar va manbalar
0 ta iqtibos0 ta foydalanilgan manba