Standard

From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak. / Mengliev, Davlatyor; Abdurakhmonova, Nilufar; Zokirova, Hulkar и др.

AIP Conference Proceedings. ред. / Niyetbay Uteuliev; Bakhtiyor Khuzhayorov; Bekzodjion Fayziev. Том 3377 American Institute of Physics Inc., 2025. 070004 (AIP Conference Proceedings; Том 3377, № 1).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференцийстатья в сборнике материалов конференциинаучнаяРецензирование

Harvard

Mengliev, D, Abdurakhmonova, N, Zokirova, H, Ibragimov, B, Jurakulova, M & Abdunazarova, M 2025, From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak. в N Uteuliev, B Khuzhayorov & B Fayziev (ред.), AIP Conference Proceedings. Том. 3377, 070004, AIP Conference Proceedings, № 1, Том. 3377, American Institute of Physics Inc., Second International Scientific and Practical Conference on Actual Problems of Mathematical Modeling and Information Technology, Nukus, Узбекистан, 12.11.2024. https://doi.org/10.1063/5.0299775

APA

Mengliev, D., Abdurakhmonova, N., Zokirova, H., Ibragimov, B., Jurakulova, M., & Abdunazarova, M. (2025). From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak. в N. Uteuliev, B. Khuzhayorov, & B. Fayziev (Ред.), AIP Conference Proceedings (Том 3377). [070004] (AIP Conference Proceedings; Том 3377, № 1). American Institute of Physics Inc.. https://doi.org/10.1063/5.0299775

Vancouver

Mengliev D, Abdurakhmonova N, Zokirova H, Ibragimov B, Jurakulova M, Abdunazarova M. From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak. в Uteuliev N, Khuzhayorov B, Fayziev B, Редакторы, AIP Conference Proceedings. Том 3377. American Institute of Physics Inc. 2025. 070004. (AIP Conference Proceedings; 1). doi: 10.1063/5.0299775

Author

Mengliev, Davlatyor ; Abdurakhmonova, Nilufar ; Zokirova, Hulkar и др. / From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak. AIP Conference Proceedings. Редактор / Niyetbay Uteuliev ; Bakhtiyor Khuzhayorov ; Bekzodjion Fayziev. Том 3377 American Institute of Physics Inc., 2025. (AIP Conference Proceedings; 1).

BibTeX

@inproceedings{22382d1669db448984bde29e9e7c3883,
title = "From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak",
abstract = "This paper presents a hybrid method for extracting named entities from medical texts in the Karakalpak language. The approach is based on a rule-oriented method that preprocesses the text in the form of morphological analysis of word forms in the text. This analysis is based on rules and a base of affixes that allow the stemming process to be carried out in order to identify the root of a word or correct misspelled words. After preprocessing, the named entities in the text are directly identified using the multilingual mBERT model. To train this language model, a sample of 5,000 sentences marked using the BIOES scheme was used. The test results showed that the hybrid approach outperforms both rule-based methods without a neural network and neural network solutions without preprocessing. The high score is supported by digital indicators, where the accuracy and recall of the model reached 90% and 90%, respectively, and the F1-measure was about 91%. In addition, the authors conducted a comparative analysis of existing solutions and provided information on the Karakalpak language.",
author = "Davlatyor Mengliev and Nilufar Abdurakhmonova and Hulkar Zokirova and Bahodir Ibragimov and Madina Jurakulova and Maftuna Abdunazarova",
year = "2025",
month = nov,
day = "7",
doi = "10.1063/5.0299775",
language = "English",
volume = "3377",
series = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",
number = "1",
editor = "Niyetbay Uteuliev and Bakhtiyor Khuzhayorov and Bekzodjion Fayziev",
booktitle = "AIP Conference Proceedings",
address = "United States",
note = "Second International Scientific and Practical Conference on Actual Problems of Mathematical Modeling and Information Technology, APMMIT2024 ; Conference date: 12-11-2024 Through 13-11-2024",

}

RIS

TY - GEN

T1 - From morphological rules to neural networks: A hybrid framework for medical entity extraction in Karakalpak

AU - Mengliev, Davlatyor

AU - Abdurakhmonova, Nilufar

AU - Zokirova, Hulkar

AU - Ibragimov, Bahodir

AU - Jurakulova, Madina

AU - Abdunazarova, Maftuna

N1 - Conference code: 2

PY - 2025/11/7

Y1 - 2025/11/7

N2 - This paper presents a hybrid method for extracting named entities from medical texts in the Karakalpak language. The approach is based on a rule-oriented method that preprocesses the text in the form of morphological analysis of word forms in the text. This analysis is based on rules and a base of affixes that allow the stemming process to be carried out in order to identify the root of a word or correct misspelled words. After preprocessing, the named entities in the text are directly identified using the multilingual mBERT model. To train this language model, a sample of 5,000 sentences marked using the BIOES scheme was used. The test results showed that the hybrid approach outperforms both rule-based methods without a neural network and neural network solutions without preprocessing. The high score is supported by digital indicators, where the accuracy and recall of the model reached 90% and 90%, respectively, and the F1-measure was about 91%. In addition, the authors conducted a comparative analysis of existing solutions and provided information on the Karakalpak language.

AB - This paper presents a hybrid method for extracting named entities from medical texts in the Karakalpak language. The approach is based on a rule-oriented method that preprocesses the text in the form of morphological analysis of word forms in the text. This analysis is based on rules and a base of affixes that allow the stemming process to be carried out in order to identify the root of a word or correct misspelled words. After preprocessing, the named entities in the text are directly identified using the multilingual mBERT model. To train this language model, a sample of 5,000 sentences marked using the BIOES scheme was used. The test results showed that the hybrid approach outperforms both rule-based methods without a neural network and neural network solutions without preprocessing. The high score is supported by digital indicators, where the accuracy and recall of the model reached 90% and 90%, respectively, and the F1-measure was about 91%. In addition, the authors conducted a comparative analysis of existing solutions and provided information on the Karakalpak language.

UR - https://www.scopus.com/pages/publications/105021378739

UR - https://www.mendeley.com/catalogue/165312ea-6316-30e7-a87e-ea7406ecb546/

U2 - 10.1063/5.0299775

DO - 10.1063/5.0299775

M3 - Conference contribution

VL - 3377

T3 - AIP Conference Proceedings

BT - AIP Conference Proceedings

A2 - Uteuliev, Niyetbay

A2 - Khuzhayorov, Bakhtiyor

A2 - Fayziev, Bekzodjion

PB - American Institute of Physics Inc.

T2 - Second International Scientific and Practical Conference on Actual Problems of Mathematical Modeling and Information Technology

Y2 - 12 November 2024 through 13 November 2024

ER -

ID: 72346981