Information Technology
Data Mining
Methods and Models in Natural Sciences
Computer analysis of texts
N.A. Kolpakov, A.I. Molodchenkov, A.V. Lukin Methods of extracting biomedical information from patents and scientific publications (on the example of chemical compounds)
N.A. Kolpakov, A.I. Molodchenkov, A.V. Lukin Methods of extracting biomedical information from patents and scientific publications (on the example of chemical compounds)
Abstract. 

This article proposes an algorithm for solving the problem of extracting information from biomedical patents and scientific publications. The introduced algorithm is based on machine learning methods. Experiments were carried out on patents from the USPTO database. Experiments have shown that the best extraction quality was achieved by a model based on BioBERT.

Keywords: 

machine learning, natural language processing, named entity recognition, biomedical texts processing.

PP. 159-166.

DOI: 10.14357/20790279230118

2024-74-1
2023-73-4
2023-73-3
2023-73-2

© ФИЦ ИУ РАН 2008-2018. Создание сайта "РосИнтернет технологии".