@book{cd208a1a515c4aebacff9d59101a4452,
title = "MIREX: MapReduce Information Retrieval Experiments",
abstract = "We propose to use MapReduce to quickly test new retrieval approaches on a cluster of machines by sequentially scanning all documents. We present a small case study in which we use a cluster of 15 low cost machines to search a web crawl of 0.5 billion pages showing that sequential scanning is a viable approach to running large-scale information retrieval experiments with little effort. The code is available to other researchers at: http://sourceforge.net/projects/mirex/",
keywords = "METIS-270790, IR-71078, EWI-17797",
author = "Djoerd Hiemstra and C. Hauff",
year = "2010",
month = apr,
day = "14",
language = "Undefined",
series = "CTIT Technical Report Series",
publisher = "Centre for Telematics and Information Technology (CTIT)",
number = "TR-CTIT-10-15",
address = "Netherlands",
}