首页> Computers in biology and medicine> Infusing clinical knowledge into language models by subword optimisation and embedding initialisation.

Infusing clinical knowledge into language models by subword optimisation and embedding initialisation.

导出 LinkOut

翻译打印收藏纠错

第一作者： Abul,Hasan

第一单位： University College London, Institute of Health Informatics, 222 Euston Rd., London, NW1 2DA, UK. Electronic address: abul.hasan@phc.ox.ac.uk.

作者： Abul,Hasan ^[1] ; Jinge,Wu ^[2] ; Quang Ngoc,Nguyen ^[2] ; Salomé,Andres ^[3] ; Imane,Guellil ^[3] ; Huayu,Zhang ^[3] ; Arlene,Casey ^[3] ; Beatrice,Alex ^[4] ; Bruce,Guthrie ^[3] ; Honghan,Wu ^[5]

作者单位： University College London, Institute of Health Informatics, 222 Euston Rd., London, NW1 2DA, UK. Electronic address: abul.hasan@phc.ox.ac.uk. ^[1] University College London, Institute of Health Informatics, 222 Euston Rd., London, NW1 2DA, UK. ^[2] Advanced Care Research Centre, Usher Institute, University of Edinburgh, UK. ^[3] Advanced Care Research Centre, Usher Institute, University of Edinburgh, UK; School of Literatures, Languages and Cultures, University of Edinburgh, UK; Edinburgh Futures Institute, University of Edinburgh, UK. ^[4] University College London, Institute of Health Informatics, 222 Euston Rd., London, NW1 2DA, UK; School of Health and Wellbeing, University of Glasgow, UK. Electronic address: honghan.wu@ucl.ac.uk. ^[5]

关键词 BERT Clinical concept and relation extraction Document classification ICD-9 coding classification Language model Phenotype identification Tokenisation

医学主题词人类(Humans);自然语言处理(Natural Language Processing);统一医学语言系统(Unified Medical Language System);语义学(Semantics);数据挖掘(Data Mining)

DOI 10.1016/j.compbiomed.2025.110747

PMID 40779989

发布时间 2025-09-04

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交