Machine Learning and Friends Lunch

home
past talks
resources
conferences

Relevance Models: An application in the Real World

Abstract

In this short talk, I'll present some interesting results of using Relevance Models to improve retrieval performance in a real life setting. In this particular case, I will show how a large collection of categorized data can be used as a form of relevance feedback. Special attention will be given to the quality and time-performance of the solution.

Reference Paper:
Zhai C. and Lafferty J., Model-based feedback in the Language Modeling Approach to Information Retrieval, CIKM, 2003