Semantic Similarity Ranking With Relevance Scoring

via “semantic-similarity-scoring-between-text-pairs”

feature-extraction model by undefined. 1,17,45,865 downloads.

Unique: Embeddings are pre-normalized to unit vectors during generation, eliminating the need for post-hoc normalization in similarity computation — this design choice reduces latency for high-throughput ranking scenarios by ~15% compared to models requiring explicit normalization

vs others: Faster similarity computation than sparse BM25 for large-scale ranking due to vector normalization baked into the model, while maintaining competitive NDCG scores on MTEB benchmarks