English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Clinical data in hospitals are increasingly accessible for research throughclinical data warehouses. However these documents are unstructured and it istherefore necessary to extract information from medical reports to conductclinical studies. Transfer learning with BERT-like models such as CamemBERT hasallowed major advances for French, especially for named entity recognition.However, these models are trained for plain language and are less efficient onbiomedical data. Addressing this gap, we introduce CamemBERT-bio, a dedicatedFrench biomedical model derived from a new public French biomedical dataset.Through continual pre-training of the original CamemBERT, CamemBERT-bioachieves an improvement of 2.54 points of F1-score on average across variousbiomedical named entity recognition tasks, reinforcing the potential ofcontinual pre-training as an equally proficient yet less computationallyintensive alternative to training from scratch. Additionally, we highlight theimportance of using a standard evaluation protocol that provides a clear viewof the current state-of-the-art for French biomedical models.

CamemBERT-bio: Leveraging Continual Pre-training for Cost-Effective Models on French Biomedical Data