lecture9-queryexpansion-handout-6-per

E with 1 or harmonic mean is a conservave average

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: 2P + R   Global methods   Query expansion   Thesauri   Automa*c thesaurus genera*on   Local methods   People usually use balanced F1 measure   Relevance feedback   Pseudo relevance feedback   i.e., with β = 1 or α = ½   Harmonic mean is a conserva*ve average   See CJ van Rijsbergen, Informa)on Retrieval 5 1 Introduc)on to Informa)on Retrieval Sec. 9.1 Relevance Feedback Introduc)on to Informa)on Retrieval Sec. 9.1 Relevance feedback   Relevance feedback: user feedback on relevance of docs in ini*al set of results   User issues a (short, simple) query   The user marks some results as relevant or non ­relevant.   The system computes a beier representa*on of the informa*on need based on feedback.   Relevance feedback can go through one or more itera*ons.   We will use ad hoc retrieval to refer to regular retrieval without relevance feedback.   We now look at four examples of relevance feedback that highlight different aspects.   Idea: it may be difficult to formulate a good query when you don’t know the collec*on well, so iterate Introduc)on to Informa)on Retrieval Similar pages Introduc)on to Informa)on Retrieval Sec. 9.1.1 Relevance Feedback: Example   Image search engine hip://nayana.ece.ucsb.edu/ imsearch/imsearch.html Introduc)on to Informa)on Retrieval Results for Ini*al Query Sec. 9.1.1 Introduc)on to Informa)on Retrieval Sec. 9.1.1 Relevance Feedback 2 Introduc)on to Informa)on Retrieval Sec. 9.1.1 source: Fernando Diaz source: Fernando Diaz Ad hoc results for query c...
View Full Document

This document was uploaded on 02/26/2014.

Ask a homework question - tutors are online