IR-part2

# We will use document frequency df to capture this

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

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ant. §༊  Relevance does not increase propor*onally with term frequency. NB: frequency = count in IR Introduc)on to Informa)on Retrieval Sec. 6.2 Log- frequency weigh*ng §༊  The log frequency weight of term t in d is wt,d ⎧ྏ1 + log10 tft,d , = ⎨ྏ 0, ⎩ྏ if tft,d > 0 otherwise §༊  Score for a document- query pair: sum over terms t in both q and d: §༊  score = t∈q∩d (1 + log tft ,d ) ∑ §༊  The score is 0 if none of the query terms is present in the document. Introduc)on to Informa)on Retrieval Sec. 6.2 Log- frequency weigh*ng §༊  The log frequency weight of term t in d is wt,d ⎧ྏ1 + log10 tft,d , = ⎨ྏ 0, ⎩ྏ if tft,d > 0 otherwise §༊  0 → 0, 1 → 1, 2 → 1.3, 10 → 2, 1000 → 4, etc. §༊  Score for a document- query pair: sum over terms t in both q and d: §༊  score = t∈q∩d (1 + log tft ,d ) ∑ §༊  The score is 0 if none of the query terms is present in the document. Introduc)on to Informa)on Retrieval Introduc*on to Informa(on Retrieval Term f...
View Full Document

## This document was uploaded on 02/14/2014.

Ask a homework question - tutors are online