Bridging Language Gaps in Multilingual Embeddings via Contrastive Learning

from blog Simon Willison's Weblog, | ↗ original
Bridging Language Gaps in Multilingual Embeddings via Contrastive Learning Most text embeddings models suffer from a "language gap", where phrases in different languages with the same semantic meaning end up with embedding vectors that aren't clustered together. Jina claim their new jina-embeddings-v3 (CC BY-NC 4.0, which means you need to...