OverviewLeaderboard
Overview
Graded semantic similarity of 100 pairs of biomedical sentences (BIOSSES, citing sentences rated 0-4 by five experts): Pearson and Spearman correlation between the cosine of a model's sentence embeddings and the mean expert rating, with no training.
Leaderboard
Ranked results, with their source, uncertainty and floors, the protocol and a sample of the data are on the Leaderboard tab.