AI NEWS.ccminicoil-v1
It creates 4-dimensional embeddings for each word stem, capturing the word's meaning. These meaning embeddings are combined into a bag-of-words (BoW) representation of the input text. The final sparse representation is calculated by weighting each word using the BM25 scoring formula. In the case of a word's absence in the miniCOIL vocabulary, word weight in sparse representation is purely based on the BM25 score. > Note: This model was designed with Qdrant's specifics in mind; miniCOIL sparse vectors in Qdrant have to be configured with Modifier.IDF. Otherwise, you'll have to personally calculate & scale the produced sparse representations by the IDF part of the BM25 formula.
번역 준비 중입니다. 원문을 표시합니다.
It creates 4-dimensional embeddings for each word stem, capturing the word's meaning. These meaning embeddings are combined into a bag-of-words (BoW) representation of the input text. The final sparse representation is calculated by weighting each word using the BM25 scoring formula. In the case of a word's absence in the miniCOIL vocabulary, word weight in sparse representation is purely based on the BM25 score. > Note: This model was designed with Qdrant's specifics in mind; miniCOIL sparse vectors in Qdrant have to be configured with Modifier.IDF. Otherwise, you'll have to personally calculate & scale the produced sparse representations by the IDF part of the BM25 formula.