@inproceedings{fd7c4ca6c94d4554a85d28364c4dccb8,
title = "Comparison of Word and Character Level Information for Medical Term Identification Using Convolutional Neural Networks and Transformers",
abstract = "Complexity and domain-specificity make medical text hard to understand for patients and their next of kin. To simplify such text, this paper explored how word and character level information can be leveraged to identify medical terms when training data is limited. We created a dataset of medical and general terms using the Human Disease Ontology from BioPortal and Wikipedia pages. Our results from 10-fold cross validation indicated that convolutional neural networks (CNNs) and transformers perform competitively. The best F score of 93.9% was achieved by a CNN trained on both word and character level embeddings. Statistical significance tests demonstrated that general word embeddings provide rich word representations for medical term identification. Consequently, focusing on words is favorable for medical term identification if using deep learning architectures.",
keywords = "Terminology, deep learning, text simplification, word embedding",
author = "Sandaru Seneviratne and Artem Lenskiy and Christopher Nolan and Eleni Daskalaki and Hanna Suominen",
note = "Publisher Copyright: {\textcopyright} 2021 International Medical Informatics Association (IMIA) and IOS Press.; 15th International Congress in Nursing Informatics: Nurses and Midwives in the Digital Age, NI 2021 ; Conference date: 23-08-2021 Through 02-09-2021",
year = "2021",
month = dec,
day = "15",
doi = "10.3233/SHTI210717",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press BV",
pages = "249--253",
editor = "Michelle Honey and Charlene Ronquillo and Ting-Ting Lee and Lucy Westbrooke",
booktitle = "Nurses and Midwives in the Digital Age - Selected Papers, Posters and Panels from the 15th International Congress in Nursing Informatics",
address = "Netherlands",
}