Fine-Tuning Models for Biomedical Relation Extraction
This paper presents pre-trained models (PTMs) for the automatic extraction of relations from biomedical text, specifically targeting the variant-phenotype domain and demonstrates that fine-tuning small BERT-based models, particularly DeBERTa, yields strong performance, approaching the current state-of-the-art (SOTA).
Claudiu Creanga, L. Dinu, Daniela Gîfu
· 0 citations