Skip to content
Publications

Talk · AIP conference proceedings · January 1, 2024

Developing a dictionary-centric named entity recognition system for Karakalpak language

Davlatyor B. Mengliev, Владимир Борисович Барахнин, Azizbek Sultonboyev, Bahodir B. Ibragimov, Mukhriddin O. Eshkulov, Ruslan Abdullayev

Abstract

This article presents an original approach to recognizing named entities in Karakalpak language texts. The approach involves the author’s algorithm, which uses dictionaries with marked words, as well as a dataset of affixes for correct morphological analysis. The proposed approach shows high efficiency, although it is limited by the set of words added to the dictionary of marked words. For the most complete understanding of the research work, the authors included the necessary information on the Karakalpak language and its morphology. To objectively assess the results of the study, the authors conducted a comparative analysis with alternative works, where they demonstrated the main advantages and disadvantages of each similar solution.

Natural Language Processing TechniquesTopic ModelingAdvanced Text Analysis Techniquesnamed entity recognitionKarakalpak languageaffixes

More by Mukhriddin Eshkulov