KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling

Abstract

Currently, Medical Subject Headings (MeSH) are manually assigned to every biomedical article published and subsequently recorded in the PubMed database to facilitate retrieving relevant information. With the rapid growth of the PubMed database, large-scale biomedical document indexing becomes increasingly important. MeSH indexing is a challenging task for machine learning, as it needs to assign multiple labels to each article from an extremely large hierachically organized collection. To address this challenge, we propose KenMeSH, an end-to-end model that combines new text features and a dynamic Knowledge-enhanced mask attention that integrates document features with MeSH label hierarchy and journal correlation features to index MeSH terms. Experimental results show the proposed method achieves state-of-the-art performance on a number of measures.

MeSHup: A Corpus for Full Text Biomedical Document Indexing

“…BioASQ provides annotated PubMed articles with the title and abstract only, and participants can tune their annotation models accordingly. Many effective indexing systems have been proposed since then, such as MeSH-Labeler (Liu et al, 2015), DeepMeSH (Peng et al, 2016), AttentionMeSH (Jin et al, 2018), MeSHProbeNet (Xun et al, 2019), and Ken-MeSH (Wang et al, 2022). MeSHLabeler and DeepMeSH are models based on a Learningto-Rank (LTR) framework.…”