A neuro-symbolic method for understanding free-text medical evidence.

Tian KangAli TurfahJaehyun KimAdler Perotte Chunhua Weng

Published in: Journal of the American Medical Informatics Association : JAMIA (2021)

MD-informed attention empowers neural reading comprehension models with interpretability and generalizability via reusable domain knowledge. Its compositionality can benefit any transformer-based architecture for machine reading comprehension of free-text medical evidence.

Keyphrases

working memory
healthcare
smoking cessation
deep learning
neural network