Biomedical Named Entity Recognition presents significant challenges due to the complexity of biomedical terminology and inconsistencies in annotation across datasets. This paper introduces SRU-NER (Slot-based Recurrent Unit NER), a novel approach designed to handle nested named entities while integrating multiple datasets through an effective multi-task learning strategy. SRU-NER mitigates annotation gaps by dynamically adjusting loss computation to avoid penalizing predictions of entity types absent in a given dataset. Through extensive experiments, including a cross-corpus evaluation and human assessment of the model's predictions, SRU-NER achieves competitive performance in biomedical and general-domain NER tasks, while improving cross-domain generalization.
@article{arxiv.2507.18542,
title = {Effective Multi-Task Learning for Biomedical Named Entity Recognition},
author = {João Ruano and Gonçalo M. Correia and Leonor Barreiros and Afonso Mendes},
journal= {arXiv preprint arXiv:2507.18542},
year = {2025}
}
Comments
Accepted at the 24th BioNLP workshop (ACL2025), 15 pages, 3 figures