yikuan8

Clinical-Longformer is a clinical knowledge enriched version of Longformer that was further pre-trained using MIMIC-III clinical notes. It allows up to 4,096 tokens as the model input. Clinical-Longformer consistently out-performs ClinicalBERT across 10 baseline dataset for at least 2 percent. Those downstream experiments broadly cover named entity recognition (NER), question answering (QA), natural language inference (NLI) and text classification tasks. For more details, please refer to our paper. We also provide a sister model at Clinical-BigBIrd Pre-training We initialized Clinical-Longformer from the pre-trained weights of the base version of Longformer. The pre-training process was distributed in parallel to 6 32GB Tesla V100 GPUs. FP16 precision was enabled to accelerate training. We pre-trained Clinical-Longformer for 200,000 steps with batch size of 6×3. The learning rates were 3e-5 for both models. The entire pre-training process took more than 2 weeks. Citing If you find our model helps, please consider citing this :) Questions Please email [email protected]