Standard

Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition. / Mengliev, Davlatyor; Barakhnin, Vladimir; Madirimov, Shohrux et al.

In: AIP Conference Proceedings, Vol. 3244, No. 1, 030012, 27.11.2024.

Research output: Contribution to journal › Conference article › peer-review

Harvard

Mengliev, D, Barakhnin, V, Madirimov, S, Ibragimov, B, Eshkulov, M & Saidov, B 2024, 'Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition', AIP Conference Proceedings, vol. 3244, no. 1, 030012. https://doi.org/10.1063/5.0241409

APA

Mengliev, D., Barakhnin, V., Madirimov, S., Ibragimov, B., Eshkulov, M., & Saidov, B. (2024). Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition. AIP Conference Proceedings, 3244(1), [030012]. https://doi.org/10.1063/5.0241409

Vancouver

Mengliev D, Barakhnin V, Madirimov S, Ibragimov B, Eshkulov M, Saidov B. Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition. AIP Conference Proceedings. 2024 Nov 27;3244(1):030012. doi: 10.1063/5.0241409

Author

Mengliev, Davlatyor ; Barakhnin, Vladimir ; Madirimov, Shohrux et al. / Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition. In: AIP Conference Proceedings. 2024 ; Vol. 3244, No. 1.

BibTeX

@article{2f1a336d32ed4b2388e02525484ea72b,
title = "Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition",
abstract = "The study presents an algorithm for recognizing dialects of Uzbek language, which is one of the low-resource languages. The authors did research about related works in this field, and included results of brief comparative analysis in second sub-section of the manuscript. Moreover, during the study a rule-based algorithm for dialect detection was developed, which uses 100 000 words dictionaries for each dialect in the analysis process. This approach differs from existing solutions by its transparency in the analysis process of the words, which allows tracking each step of the algorithm. For more optimized performance of the algorithm, the authors divided the corpus of each dialect into dictionaries, each dialect has 28 dictionaries and thus 140 dictionaries were generated. Testing of the algorithm showed its high accuracy in identifying dialect words and processing mixed dialect entries.",
author = "Davlatyor Mengliev and Vladimir Barakhnin and Shohrux Madirimov and Bahodir Ibragimov and Mukhriddin Eshkulov and Bobur Saidov",
year = "2024",
month = nov,
day = "27",
doi = "10.1063/5.0241409",
language = "English",
volume = "3244",
journal = "AIP Conference Proceedings",
issn = "0094-243X",
publisher = "American Institute of Physics",
number = "1",
note = "2024 International Scientific Conference on Modern Problems of Applied Science and Engineering, MPASE 2024 ; Conference date: 02-05-2024 Through 03-05-2024",

}

RIS

TY - JOUR

T1 - Unveiling the Variance of Uzbek language: A Rule-Based Algorithm for Dialect Recognition

AU - Mengliev, Davlatyor

AU - Barakhnin, Vladimir

AU - Madirimov, Shohrux

AU - Ibragimov, Bahodir

AU - Eshkulov, Mukhriddin

AU - Saidov, Bobur

PY - 2024/11/27

Y1 - 2024/11/27

N2 - The study presents an algorithm for recognizing dialects of Uzbek language, which is one of the low-resource languages. The authors did research about related works in this field, and included results of brief comparative analysis in second sub-section of the manuscript. Moreover, during the study a rule-based algorithm for dialect detection was developed, which uses 100 000 words dictionaries for each dialect in the analysis process. This approach differs from existing solutions by its transparency in the analysis process of the words, which allows tracking each step of the algorithm. For more optimized performance of the algorithm, the authors divided the corpus of each dialect into dictionaries, each dialect has 28 dictionaries and thus 140 dictionaries were generated. Testing of the algorithm showed its high accuracy in identifying dialect words and processing mixed dialect entries.

AB - The study presents an algorithm for recognizing dialects of Uzbek language, which is one of the low-resource languages. The authors did research about related works in this field, and included results of brief comparative analysis in second sub-section of the manuscript. Moreover, during the study a rule-based algorithm for dialect detection was developed, which uses 100 000 words dictionaries for each dialect in the analysis process. This approach differs from existing solutions by its transparency in the analysis process of the words, which allows tracking each step of the algorithm. For more optimized performance of the algorithm, the authors divided the corpus of each dialect into dictionaries, each dialect has 28 dictionaries and thus 140 dictionaries were generated. Testing of the algorithm showed its high accuracy in identifying dialect words and processing mixed dialect entries.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85212103757&origin=inward&txGid=d95a6c241859fd3b1f5d68371fc0af84

UR - https://www.mendeley.com/catalogue/04ab98e8-40f9-3f5f-86eb-6ca3673c8747/

U2 - 10.1063/5.0241409

DO - 10.1063/5.0241409

M3 - Conference article

VL - 3244

JO - AIP Conference Proceedings

JF - AIP Conference Proceedings

SN - 0094-243X

IS - 1

M1 - 030012

T2 - 2024 International Scientific Conference on Modern Problems of Applied Science and Engineering

Y2 - 2 May 2024 through 3 May 2024

ER -

ID: 61408074