IR-part2

Recall on the web recall seldom marers what marers

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: judgments of whether documents are relevant to queries Then we can use Precision/Recall/F measure as before §༊  Evalua*on of ranked results: §༊  The system can return any number of results §༊  By taking various numbers of the top returned documents (levels of recall), the evaluator can produce a precision- recall curve 71 Introduc)on to Informa)on Retrieval Recall/Precision R P §༊  §༊  §༊  §༊  §༊  §༊  §༊  §༊  §༊  §༊  1 2 3 4 5 6 7 8 9 10 R N N R R N R N N N Assume 10 rel docs in collection Introduc)on to Informa)on Retrieval Sec. 8.4 A precision- recall curve 1.0 Precision 0.8 0.6 0.4 0.2 0.0 0.0 0.2 0.4 0.6 0.8 1.0 Recall 73 Introduc)on to Informa)on Retrieval Sec. 8.4 Averaging over queries §༊  A precision- recall graph for one query isn’t a very sensible thing to look at §༊  You need to average performance over a whole bunch of queries. §༊  But there’s a technical issue: §༊  Precision- recall calcula*ons place some points on the graph §༊  How do you determine a value (interpolate) between the points? 74 Introduc)on to Informa)on Retrieval Sec. 8.4 Inte...
View Full Document

Ask a homework question - tutors are online