Information Retrieval (IR) expert parameters: ir_minidf

Parameter

ir_minidf

Description

This parameter defines the minimum relevance ranking that search terms must have for Service Manager to include them in Information Retrieval (IR) search results. Service Manager ranks each search term based on how frequently it appears in the index. Terms that appear in the index less frequently are assigned more relevance in search results. If a term appears in the index too frequently, Service Manager ignores the search term as if it were in the stop word list.

Service Manager determines a relevance ranking for each search term by computing an IDF value. Service Manager uses the following formula to compute the IDF value of search terms: [natural log (terms in index/number of instances of search term in index)]+1

For example, in an index of 1000 terms, a search term that appears 250 times in the index has an IDF value of 2.4. Since this is below the minimum value of 2.5, Service Manager ignores the term because it appears too frequently. A search term that appears only 10 times in the index however has an IDF value of 5.6, and since this term exceeds the minimum IDF value threshold, Service Manager includes it in the search results.

Valid if set from

Server's operating system command prompt

Initialization file (sm.ini)

Requires restart of the Service Manager server?

Yes

Default value

2.5

Possible values

Minimum IDF value

Example usage

Command line: sm -httpPort:13080 -ir_minidf:2.4

Initialization file: ir_minidf:2.4

Related topics

Information Retrieval (IR) expert parameters
Information Retrieval (IR) expert parameters: ir_term_drop_off