bsuirДоклады БГУИРDoklady BGUIR1729-76482708-0382БГУИР10.35596/1729-7648-2019-123-5-60-65bsuir-1152Research ArticleЭЛЕКТРОНИКА, РАДИОФИЗИКА, РАДИОТЕХНИКА, ИНФОРМАТИКАELECTRONICS, RADIOPHYSICS, RADIOENGINEERING, INFORMATICSАнализ методов разрешения лексической многозначности в области биомедициныAnalysis of the methods of word sense disambiguation in the biomedical domainПашукА. В.PashukA. V.

Пашук Александр Владимирович - аспирант кафедры систем управления.

220013, Минск, ул. П. Бровки, 6, тел. +375-29-875-23-34

Pashuk Aleksandr Vladimirovich - PG student of the control systems department.

220013, Minsk, P. Brovka str., 6, tel. +375-29-875-23-34

pashuk@bsuir.byГуриновичА. Б.GurinovichA. B.

Кандидат физико-математических наук, доцент кафедры вычислительных методов и программирования.

220013, Минск, ул. П. Бровки, 6

PhD, associate professor of computational methods and programming department.

220013, Minsk, P. Brovka str., 6

ВолороваН. А.VolorovaN. A.

Кандидат технических наук, доцент кафедры информатики.

220013, Минск, ул. П. Бровки, 6

PhD, associate professor of the informatics department of Belarusian state university of informatics and radioelectronics.

220013, Minsk, P. Brovka str., 6

КузнецовА. П.KuznetsovA. P.

Доктор технических наук, профессор кафедры систем управления.

220013, Минск, ул. П. Бровки, 6

D.Sci, professor of control systems department.

220013, Minsk, P. Brovka str., 6

Белорусский государственный университет информатики и радиоэлектроникиBelarusian state university of informatics and radioelectronics201903072019056065Copyright © Пашук А.В., Гуринович А.Б., Волорова Н.А., Кузнецов А.П., 20192019Пашук А.В., Гуринович А.Б., Волорова Н.А., Кузнецов А.П.Pashuk A.V., Gurinovich A.B., Volorova N.A., Kuznetsov A.P.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.bsuir.by/jour/article/view/1152

Предложен метод разрешения лексической многозначности биомедицинских терминов на основе сравнения «мешков слов», полученных из контекста, определений и информации о связанных терминах из метатезауруса UMLS [1], а также модификация метода с использованием оценки важности слов с помощью статистической меры TF-IDF. Проведена экспериментальная проверка метода на открытом тестовом наборе данных MSH WSD [2], разработанном с целью поддержки исследований в области разрешения лексической многозначности.

A method for resolving the lexical ambiguity of biomedical terms has been proposed. The method is based on a comparison of «word bags» obtained from the context, definitions and information on related terms from the UMLS metathesaurus [1]. Modification of the method using the analysis of word importance using the statistical measure TF-IDF has been proposed. Experimental verification of the method has been performed on the open test MSH WSD data set [2], developed to support research in the field of lexical resolution.

машинное обучениеобработка текста естественного языкаразрешение лексической многозначностиизвлечение информацииmachine learningnatural language processingword sense disambiguationinformation retrievalReferences. Unified Medical Language System (UMLS) // U.S. National Library of Medicine. URL: https://www.nlm.nih.gov/research/umls/ (date of access: 20.11.2018).. Unified Medical Language System (UMLS) // U.S. National Library of Medicine. URL: https://www.nlm.nih.gov/research/umls/ (date of access: 20.11.2018).Word Sense Disambiguation (WSD) Test Collections // U.S. National Library of Medicine. URL: https://wsd.nlm.nih.gov/ (date of access: 30.11.2018).Word Sense Disambiguation (WSD) Test Collections // U.S. National Library of Medicine. URL: https://wsd.nlm.nih.gov/ (date of access: 30.11.2018).Statistical Reports on MEDLINE/PubMed Baseline Data // U.S. National Library of Medicine. URL: https://www.nlm.nih.gov/bsd/licensee/baselinestats.html (date of access: 16.11.2018).Statistical Reports on MEDLINE/PubMed Baseline Data // U.S. National Library of Medicine. URL: https://www.nlm.nih.gov/bsd/licensee/baselinestats.html (date of access: 16.11.2018).Ide N., Veronis J. Introduction to the special issue on word sense disambiguation: the state of the art // Computational Linguistics - Special issue on word sense disambiguation. 1998. № 24. P. 2-40.Ide N., Veronis J. Introduction to the special issue on word sense disambiguation: the state of the art // Computational Linguistics - Special issue on word sense disambiguation. 1998. № 24. P. 2-40.Navigli R. Word sense disambiguation: a survey // ACM Computing Surveys. 2009. № 41. P. 1-69.Navigli R. Word sense disambiguation: a survey // ACM Computing Surveys. 2009. № 41. P. 1-69.Lesk M. Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone // Proceeding SIGDOC '86 Proceedings of the 5th annual international conference on Systems documentation. Toronto, Ontario, Canada: ACM, 1986. P. 24-26.Lesk M. Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone // Proceeding SIGDOC '86 Proceedings of the 5th annual international conference on Systems documentation. Toronto, Ontario, Canada: ACM, 1986. P. 24-26.Leacock C., Miller G.A. Using corpus statistics and WordNet relations for sense identification // Computational Linguistics - Special issue on word sense disambiguation. 1998. № 24. P. 147-165.Leacock C., Miller G.A. Using corpus statistics and WordNet relations for sense identification // Computational Linguistics - Special issue on word sense disambiguation. 1998. № 24. P. 147-165.Preiss J., Stevenson M. DALE: A Word Sense Disambiguation System for Biomedical Documents Trained using Automatically Labeled Examples // Proceedings of the 2013 NAACL HLT Demonstration Session. Atlanta, Georgia: Association for Computational Linguistics, 2013. P. 1-4.Preiss J., Stevenson M. DALE: A Word Sense Disambiguation System for Biomedical Documents Trained using Automatically Labeled Examples // Proceedings of the 2013 NAACL HLT Demonstration Session. Atlanta, Georgia: Association for Computational Linguistics, 2013. P. 1-4.Liu H., Teller V., Friedman C.A Multi-aspect Comparison Study of Supervised Word Sense Disambiguation // Journal of the American Medical Informatics Association. 2004. № 11. P. 320-331.Liu H., Teller V., Friedman C.A Multi-aspect Comparison Study of Supervised Word Sense Disambiguation // Journal of the American Medical Informatics Association. 2004. № 11. P. 320-331.Word sense disambiguation across two domains: Biomedical literature and clinical notes / G.K. Savova [et al.] // Journal of Biomedical Informatics. 2008. № 41. P. 1088-1100.Word sense disambiguation across two domains: Biomedical literature and clinical notes / G.K. Savova [et al.] // Journal of Biomedical Informatics. 2008. № 41. P. 1088-1100.Jimeno-Yepes A. J., Aronson A. R. Knowledge-based biomedical word sense disambiguation: comparison of approaches // BMC Bioinformatics. 2010. № 11. P. 569-581.Jimeno-Yepes A. J., Aronson A. R. Knowledge-based biomedical word sense disambiguation: comparison of approaches // BMC Bioinformatics. 2010. № 11. P. 569-581.

The authors declare that there are no conflicts of interest present.