Enhancing Automatic PT Tagging for MEDLINE Citations Using Transformer-Based Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cid, Victor H., Mork, James
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908392341110784
author Cid, Victor H.
Mork, James
author_facet Cid, Victor H.
Mork, James
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03321
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Automatic PT Tagging for MEDLINE Citations Using Transformer-Based Models
Cid, Victor H.
Mork, James
Digital Libraries
Machine Learning
I.2.7; H.3.3; H.3.5
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.
title Enhancing Automatic PT Tagging for MEDLINE Citations Using Transformer-Based Models
topic Digital Libraries
Machine Learning
I.2.7; H.3.3; H.3.5
url https://arxiv.org/abs/2506.03321