IR-part2

Sec 63 introducon to informaon retrieval sec

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: he collec*on, coun*ng mul*ple occurrences. §༊  Example: Word insurance Collection frequency 10440 Document frequency 3997 10422 8760 try §༊  Which word is a berer search term (and should get a higher weight)? Introduc)on to Informa)on Retrieval Introduc*on to Informa(on Retrieval (Inverse) Document frequency weigh*ng Introduc)on to Informa)on Retrieval Introduc*on to Informa(on Retrieval k- idf weigh*ng Introduc)on to Informa)on Retrieval Sec. 6.2.2 k- idf weigh*ng §༊  The k- idf weight of a term is the product of its k weight and its idf weight. w = (1 + log tf ) × log ( N / df ) t ,d t ,d 10 t §༊  Best known weigh*ng scheme in informa*on retrieval §༊  Note: the “- ” in k- idf is a hyphen, not a minus sign! §༊  Alterna*ve names: k.idf, k x idf §༊  Increases with the number of occurrences within a document §༊  Increases with the rarity of the term in the collec*on Introduc)on to Informa)on Retrieval Sec. 6.2.2 Final ranking of documents for a query Score(q, d ) = ∑ t ∈q∩d tf.idft ,d 34 Introduc)on to Informa)on Retrieval...
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online