BM25

Synonyms

OKAPI retrieval function; Probabilistic model

Definition

BM25 is a ranking function that ranks a set of documents based on the query terms appearing in each document, regardless of the inter-relationship between the query terms within a document (e.g., their relative proximity). It is not a single function, but actually a whole family of scoring functions, with slightly different components and parameters. It is used by search engines to rank matching documents according to their relevance to a given search query and is often referred to as “Okapi BM25,” since the Okapi information retrieval system was the first system implementing this function. The BM25 retrieval formula belongs to the BM family of retrieval models (BM stands for Best Match), that is the weight of a term t in a document d is:

$${{\bf{tf}} \over {k +{\bf{tf}}}}\,\ln\,{{(r_{\bf{t}} + 0.5)\, \cdot\,({\bf{N}}\, - \,R\, - \,{\bf{n_t}}\, + \, r_{\bf{t}}\, + \,0.5)} \over {({\bf{n_t}} \, - \,r_{\bf{t}}\, + 0.5)\,...