A systematic comparison of soft inter-rater reliability measures for free-text biomedical annotations finds that NLI-based measures are the most robust compromise.
Measuring Agreement on Set-valued Items (
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Consensus Measures for Unstructured Biomedical Text Annotations
A systematic comparison of soft inter-rater reliability measures for free-text biomedical annotations finds that NLI-based measures are the most robust compromise.