Reputation: 31
Can anybody explain it to me what is bm-25 and how it differs from tf-idf which was previously used and Why Elasticsearch in version 5.0+ changed their scoring algorithm from tf-idf to bm25.
Upvotes: 3
Views: 3919
Reputation: 1336
BM-25 is ranking function which calculates score to represent a document's relevance with respect to query. In tests this approach gives better results compared to earlier TF-IDF based scoring.
Lucene switched to BM-25 as default scoring from 6.0 - which is underlying search library used by Elasticsearch and SOLR
Upvotes: 3