sts dev Benchmark (Semantic Similarity)

0 rows 0 with code listed 10 metrics

The main objective Semantic Similarity is to measure the distance between the semantic meanings of a pair of words, phrases, sentences, or documents. For example, the word “car” is more similar to “bus” than it is to “cat”. The two main approaches to measuring Semantic Similarity are knowledge-based approaches and corpus-based, distributional methods.

Source: Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

The archive carries no text for this table; the description above is the archive's text for the task Semantic Similarity. archive 2025-07-28

Results archive 2025-07-28

No rows in the archive for this table at snapshot 2025-07-28. It declares 10 metrics (Pearson Cosine, Pearson Dot, Pearson Euclidean, Pearson Manhattan, Pearson Max, Spearman Cosine, Spearman Dot, Spearman Euclidean, Spearman Manhattan, Spearman Max) but no result was ever recorded against it. That says nothing about whether results exist elsewhere.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections