<?xml version="1.0" encoding="UTF-8"?>
<collection xmlns="http://www.loc.gov/MARC21/slim">
	<record>
		<datafield tag="980" ind1=" " ind2=" ">
			<subfield code="a">REPORT</subfield>
		</datafield>
		<datafield tag="970" ind1=" " ind2=" ">
			<subfield code="a">grangier:2004:idiap-04-02/IDIAP</subfield>
		</datafield>
		<datafield tag="245" ind1=" " ind2=" ">
			<subfield code="a">Making Retrieval Faster Through Document Clustering</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Grangier, David</subfield>
		</datafield>
		<datafield tag="700" ind1=" " ind2=" ">
			<subfield code="a">Vinciarelli, Alessandro</subfield>
		</datafield>
		<datafield tag="856" ind1="4" ind2="0">
			<subfield code="i">EXTERNAL</subfield>
			<subfield code="u">http://publications.idiap.ch/attachments/reports/2004/rr04-02.pdf</subfield>
			<subfield code="x">PUBLIC</subfield>
		</datafield>
		<datafield tag="088" ind1=" " ind2=" ">
			<subfield code="a">Idiap-RR-02-2004</subfield>
		</datafield>
		<datafield tag="260" ind1=" " ind2=" ">
			<subfield code="c">2004</subfield>
			<subfield code="b">IDIAP</subfield>
		</datafield>
		<datafield tag="520" ind1=" " ind2=" ">
			<subfield code="a">This work addresses the problem of reducing the time between query submission and results output in a retrieval system. The goal is achieved by considering only a database fraction as small as possible during the retrieval process. Our approach is based on a new clustering technique and comparisons with other clustering methods presented in the literature are performed. Our algorithm is shown to outperform the other techniques: retrieval performances close to those obtained with the whole corpus are achieved by selecting only 5\% of the data.</subfield>
		</datafield>
	</record>
</collection>