Upload
brook-emma-eaton
View
215
Download
1
Tags:
Embed Size (px)
Citation preview
With or without users?With or without users?
Julio GonzaloJulio Gonzalo
UNEDUNED
http://nlp.uned.eshttp://nlp.uned.es
The classical IR modelThe classical IR model
query
Relevant docs
(precise)Information
need
(fixed)Documentcollection
Query expansion
Formal models
Indexing
Clustering
Query/document comparison
Data structures
Weighting heuristics
Visualization
feedback
Filtering
Goal: all relevant information and only relevant information
Is Relevance what the user needs?
Most frequent questions, Infoseek 1999 (SIGIR Forum)
1. Empty question
2. sex
8. Pamela Anderson (first multiword question in the rank)
No! It is quality, saliency, reliability... In one or two links
Pagerank addresses user needsPagerank addresses user needs
www.telecinco.es
Clasificados.wanadoo.es
Realizadores.tv
Chat.rincondelvago.com
www.horanova.es
mx.dir.yahoo.com
telecinco
telecinco
telecinc
o
telecinco
telecinco
• ¡El texto de los enlaces es el más valioso para indexar!
With or without users?With or without users?
Google’s first commandment: Focus on the Google’s first commandment: Focus on the user and all the rest will come along.user and all the rest will come along.
““With or without users?” is not the right With or without users?” is not the right questionquestion
““With or without user focus?” YESWith or without user focus?” YES
Is CLEF focusing on users?Is CLEF focusing on users? Multilingual track: If I have equivalent sets of Multilingual track: If I have equivalent sets of
relevant news in many languages, I do not want a relevant news in many languages, I do not want a merged set. I want the subset in my native merged set. I want the subset in my native language!language!
Q&A track: How much does it take to find an Q&A track: How much does it take to find an answer with an IR engine? (Ask QA assessors!!)answer with an IR engine? (Ask QA assessors!!)
Interactive track: natural user task, but artificial Interactive track: natural user task, but artificial users!users!
Only image CLEF & GIRT partially pass the testOnly image CLEF & GIRT partially pass the test Why the intersection between ECDL and CLEF is Why the intersection between ECDL and CLEF is
almost null?almost null? Multilingual web track: danger of making the same Multilingual web track: danger of making the same
pre-google mistake. pre-google mistake.
The web is truly multilingual by nature...
But the web is redundant, and average users are looking for a single perfect link!! Almost no need for cross-language users (cf Google)
Vertical search engines?Vertical search engines?
Structured data
Information need Web pages
extraction
query