Comparing CRF vs BERT Models for Named Entity Recognition and Relation Extraction

This paper presents our participation in the CLEF 2025 GutBrainIE challenge, addressing tasks in Named Entity Recognition (NER) and Relation Extraction (RE) on biomedical texts related to the gut-brain axis. We explored both traditional and modern approaches, including Conditional Random Fields (CRFs) with hand-engineered features and fine-tuned BERT-based models. For RE, we focused on a simplified pipeline using BiomedBERT, coupled with NER outputs to extract binary and ternary relations. Our experiments revealed the limitations of CRFs in this domain and highlighted the variability and sensitivity of BERT-based models to training stability and dataset noise. While our NER performance was mid-ranked, we achieved competitive results in RE, particularly in ternary tag-based extraction. We also reflect on the effects of model selection, loss function design, and data configurations, offering insights for future work in biomedical IE.