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.

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.

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 -