This AI Paper from China Introduces BGE-M3: A New Member to BGE Model Series with Multi-Linguality (100+ languages)

BAAI introduces BGE M3-Embedding, a new text embedding model that supports over 100 languages, accommodates diverse retrieval functionalities, and processes input data ranging from short sentences to lengthy documents. It addresses the limitations in existing models, outperforms baseline methods, and marks a substantial step forward in information retrieval.