Focal-Loss Transformer with Feedback-Validation Learning for Imbalanced Drug Interaction Extraction
Abstract
Drug-drug interactions (DDIs) are a leading cause of preventable adverse drug events, and the standard benchmark corpus for extracting them from biomedical text is severely im-balanced towards non-interacting pairs, making rare interaction types hard to learn. We asked whether combining focal loss, entity-aware transformer encoding, and feedback-guided feature fusion in a single architecture could improve minority-class DDI extraction under this imbalance while requiring less training data than prior methods. We propose FoLT-DMCNN-FBVL, which integrates a BiomedBERT backbone with entity marker injection, a multi-branch neural classifier, and feedback-based validation learning, trained on a small balanced subset of the SemEval- 2013 DDIExtraction corpus and evaluated on the full blind test set. FoLT-DMCNN-FBVL matched the most recent state-of-the-art result (statistically indistinguishable; nominal absolute+0.33%) and significantly outperformed the widely cited CNN-DDI baseline (absolute +4.32%), while using less than one-fifth of the available training data. These findings show that a doubly imbalance-aware transformer architecture can match or exceed current state-of-the-art DDI extraction performance with substantially greater data efficiency. Such architectures could support more scalable and cost-effective pharmacovigilance and clinical NLP pipelines in settings where annotated data for rare interaction types is limited.
Related
- CBAT-Net: a unified CNN–BiLSTM–MultiHead transformer architecture for joint Q3/Q8 protein secondary structure prediction
- A novel LLM-based GPT-neo transformer with machine learning architecture for promoters prediction in Agrobacterium
- LGH-Transformer: A Hybrid CNN–Transformer Model for Multi-Class Bladder Tissue Classification from Cystoscopic Images
- Structured information extraction from geoscientific literature with GeoExtractor
- Stepwise Proteinase K Digestion Improves Genomic DNA Yield and Purity from Goat Semen: A Comparative Pilot Study of Five Extraction Protocols
BibTeX
@article{chanaa2026focalloss,
title = {{Focal-Loss Transformer with Feedback-Validation Learning for Imbalanced Drug Interaction Extraction}},
author = {Hiba Chanaa and El Habib Nfaoui and Chafik Boulealam and Chakir Loqman},
journal = {International journal of advanced computer science and applications (IJACSA)},
year = {2026},
month = sep,
doi = {10.14569/ijacsa.2026.0170897},
url = {https://hal.science/hal-05739949v1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Focal-Loss Transformer with Feedback-Validation Learning for Imbalanced Drug Interaction Extraction
AU - Hiba Chanaa
AU - El Habib Nfaoui
AU - Chafik Boulealam
AU - Chakir Loqman
PY - 2026
DA - 2026/09/06
JO - International journal of advanced computer science and applications (IJACSA)
DO - 10.14569/ijacsa.2026.0170897
UR - https://hal.science/hal-05739949v1
AB - Drug-drug interactions (DDIs) are a leading cause of preventable adverse drug events, and the standard benchmark corpus for extracting them from biomedical text is severely im-balanced towards non-interacting pairs, making rare interaction types hard to learn. We asked whether combining focal loss, entity-aware transformer encoding, and feedback-guided feature fusion in a single architecture could improve minority-class DDI extraction under this imbalance while requiring less training data than prior methods. We propose FoLT-DMCNN-FBVL, which integrates a BiomedBERT backbone with entity marker injection, a multi-branch neural classifier, and feedback-based validation learning, trained on a small balanced subset of the SemEval- 2013 DDIExtraction corpus and evaluated on the full blind test set. FoLT-DMCNN-FBVL matched the most recent state-of-the-art result (statistically indistinguishable; nominal absolute+0.33%) and significantly outperformed the widely cited CNN-DDI baseline (absolute +4.32%), while using less than one-fifth of the available training data. These findings show that a doubly imbalance-aware transformer architecture can match or exceed current state-of-the-art DDI extraction performance with substantially greater data efficiency. Such architectures could support more scalable and cost-effective pharmacovigilance and clinical NLP pipelines in settings where annotated data for rare interaction types is limited.
SN - 2158-107X
SN - 2156-5570
ER -