Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models

Published in EMNLP Findings, 2021

This paper studies parameter-efficient integration of biomedical domain knowledge into pretrained language models.

Recommended citation: Qiuhao Lu, Dejing Dou, and Thien Huu Nguyen. Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models. Findings of EMNLP, 2021.
Download Paper