Clinical ModernBERT: An efficient and long context encoder for biomedical text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Simon A., Wu, Anthony, Chiang, Jeffrey N.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913778041356288
author Lee, Simon A.
Wu, Anthony
Chiang, Jeffrey N.
author_facet Lee, Simon A.
Wu, Anthony
Chiang, Jeffrey N.
contents We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Clinical ModernBERT: An efficient and long context encoder for biomedical text
Lee, Simon A.
Wu, Anthony
Chiang, Jeffrey N.
Computation and Language
Artificial Intelligence
Machine Learning
We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks.
title Clinical ModernBERT: An efficient and long context encoder for biomedical text
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.03964