Standard

Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts. / Ismagulov, Z. s.; Kosyakov, D. v.; Guskov, A. e.

In: Automatic documentation and mathematical linguistics, Vol. 58, No. 6, 17.02.2025, p. 441-452.

Research output: Contribution to journal › Article › peer-review

Harvard

Ismagulov, ZS, Kosyakov, DV & Guskov, AE 2025, 'Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts', Automatic documentation and mathematical linguistics, vol. 58, no. 6, pp. 441-452. https://doi.org/10.3103/S0005105524700328

APA

Ismagulov, Z. S., Kosyakov, D. V., & Guskov, A. E. (2025). Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts. Automatic documentation and mathematical linguistics, 58(6), 441-452. https://doi.org/10.3103/S0005105524700328

Vancouver

Ismagulov ZS, Kosyakov DV, Guskov AE. Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts. Automatic documentation and mathematical linguistics. 2025 Feb 17;58(6):441-452. doi: 10.3103/S0005105524700328

Author

Ismagulov, Z. s. ; Kosyakov, D. v. ; Guskov, A. e. / Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts. In: Automatic documentation and mathematical linguistics. 2025 ; Vol. 58, No. 6. pp. 441-452.

BibTeX

@article{af327030305e490b86397cababa4417d,
title = "Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts",
abstract = "The processes of extracting and comparing mathematical methods from scientific publications using different approaches—large language models, machine learning based classification method, and probabilistic topic modelling—are discussed. The superiority of the model obtained with probabilistic topic modelling when studying each article separately and of the large language model when studying whole projects is revealed, as well as the significant superiority of combining the results of these two approaches.",
keywords = "PUBLICATION, PROBABILISTIC TOPIC MODELLING, MACHINE LEARNING, LARGE LANGUAGE MODEL, MATHEMATICAL METHOD",
author = "Ismagulov, {Z. s.} and Kosyakov, {D. v.} and Guskov, {A. e.}",
note = "Ismagulov, Z. S. Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts / Z. S. Ismagulov, D. V. Kosyakov, A. E. Guskov // Automatic Documentation and Mathematical Linguistics. – 2024. – Vol. 58, No. 6. – P. 441-452. – DOI 10.3103/S0005105524700328. – EDN LJZTGU.",
year = "2025",
month = feb,
day = "17",
doi = "10.3103/S0005105524700328",
language = "English",
volume = "58",
pages = "441--452",
journal = "Automatic documentation and mathematical linguistics",
issn = "0005-1055",
publisher = "Allerton Press Inc.",
number = "6",

}

RIS

TY - JOUR

T1 - Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts

AU - Ismagulov, Z. s.

AU - Kosyakov, D. v.

AU - Guskov, A. e.

N1 - Ismagulov, Z. S. Comparison of Approaches to the Extraction of Mathematical Methods from Scientific Texts / Z. S. Ismagulov, D. V. Kosyakov, A. E. Guskov // Automatic Documentation and Mathematical Linguistics. – 2024. – Vol. 58, No. 6. – P. 441-452. – DOI 10.3103/S0005105524700328. – EDN LJZTGU.

PY - 2025/2/17

Y1 - 2025/2/17

N2 - The processes of extracting and comparing mathematical methods from scientific publications using different approaches—large language models, machine learning based classification method, and probabilistic topic modelling—are discussed. The superiority of the model obtained with probabilistic topic modelling when studying each article separately and of the large language model when studying whole projects is revealed, as well as the significant superiority of combining the results of these two approaches.

AB - The processes of extracting and comparing mathematical methods from scientific publications using different approaches—large language models, machine learning based classification method, and probabilistic topic modelling—are discussed. The superiority of the model obtained with probabilistic topic modelling when studying each article separately and of the large language model when studying whole projects is revealed, as well as the significant superiority of combining the results of these two approaches.

KW - PUBLICATION

KW - PROBABILISTIC TOPIC MODELLING

KW - MACHINE LEARNING

KW - LARGE LANGUAGE MODEL

KW - MATHEMATICAL METHOD

UR - https://elibrary.ru/item.asp?id=80348692

U2 - 10.3103/S0005105524700328

DO - 10.3103/S0005105524700328

M3 - Article

VL - 58

SP - 441

EP - 452

JO - Automatic documentation and mathematical linguistics

JF - Automatic documentation and mathematical linguistics

SN - 0005-1055

IS - 6

ER -

ID: 67762355