Enhancing Automatic PT Tagging for MEDLINE Citations Using Transformer-Based Models
This work addresses limitations in automated indexing for biomedical literature retrieval, though it is incremental as it applies existing models to a specific domain.
The study tackled the problem of predicting Medical Subject Headings Publication Types from MEDLINE citation metadata by using pre-trained Transformer-based models like BERT and DistilBERT, resulting in significant improvements in tagging accuracy.
We investigated the feasibility of predicting Medical Subject Headings (MeSH) Publication Types (PTs) from MEDLINE citation metadata using pre-trained Transformer-based models BERT and DistilBERT. This study addresses limitations in the current automated indexing process, which relies on legacy NLP algorithms. We evaluated monolithic multi-label classifiers and binary classifier ensembles to enhance the retrieval of biomedical literature. Results demonstrate the potential of Transformer models to significantly improve PT tagging accuracy, paving the way for scalable, efficient biomedical indexing.