The Classification of Short Scientific Texts Using Pretrained BERT Model

Autor:	Konstantin Kotik, Yuriy N. Orlov, Gleb Danilov, Alexander Potapov, Timur Ishankulov, Michael A. Shifrin
Rok vydání:	2021
Předmět:	Topic model Binary classification Ensemble forecasting Computer science business.industry Selection (linguistics) Scientific literature Artificial intelligence computer.software_genre business computer Natural language processing Task (project management)
Zdroj:	MIE
Popis:	Automated text classification is a natural language processing (NLP) technology that could significantly facilitate scientific literature selection. A specific topical dataset of 630 article abstracts was obtained from the PubMed database. We proposed 27 parametrized options of PubMedBERT model and 4 ensemble models to solve a binary classification task on that dataset. Three hundred tests with resamples were performed in each classification approach. The best PubMedBERT model demonstrated F1-score = 0.857 while the best ensemble model reached F1-score = 0.853. We concluded that the short scientific texts classification quality might be improved using the latest state-of-art approaches.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::45838fdc67d88cc43f3b2d2b4fb8b37c https://doi.org/10.3233/shti210125 Zobrazit plný text záznamu