Reproduce “MATCH: Multi-stage Article Tagging to Concept Hierarchies” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Daniele Raimondi, Feichi Lu, Oliver Grun, Mariia Eremina, Andrea Perlato
MATCH assigns fine-grained SCALE taxonomy Concepts to scientific articles by retrieving candidates from titles, abstracts, and keywords, applying hierarchy-based filters, and using a language model to select and rank labels. In expert assessments of 110 MDPI articles, two configurations achieved 88.7% and 88.9% Precision@5, with no significant difference detected; results do not establish equivalence or transferability beyond MDPI.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.