Fusion of effective retrieval strategies in the same information retrieval system
Identifieur interne : 000996 ( Main/Exploration ); précédent : 000995; suivant : 000997Fusion of effective retrieval strategies in the same information retrieval system
Auteurs : Steven M. Beitzel [États-Unis] ; Eric C. Jensen [États-Unis] ; Abdur Chowdhury [États-Unis] ; David Grossman [États-Unis] ; Ophir Frieder [États-Unis] ; Nazli Goharian [États-Unis]Source :
- Journal of the American Society for Information Science and Technology [ 1532-2882 ] ; 2004-08.
English descriptors
- Teeft :
- Algorithm, American society, Annual text retrieval conference nist, Aslam, Average number, Average precision, Best trec systems, Chowdhury, Combmnz, Component result, Component result sets, Component sets, Component systems, Data fusion, Data fusion techniques, Different document retrieval strategies, Different query representations, Different retrieval strategies, Different systems, Document, Document analysis, Effective result sets, Effective retrieval strategies, Effective strategies, Effectiveness improvements, Frieder, Fusion, Fusion techniques, Future work, Grossman, High rank, High ranks, Information retrieval, Information retrieval systems, Information science, Knowledge management, Large number, Montague, Multiple pieces, Other factors, Overlap, Overlap analysis, Overlap correlation, Overlap hypothesis, Phrase processing, Poor indicator, Query, Query representations, Rank displacement, Relevance feedback, Relevant documents, Relevant overlap, Result sets, Retrieval, Retrieval effectiveness, Retrieval strategies, Retrieval strategy, Same information retrieval system, Same system, Sigir, Systemic differences, Trec.
Abstract
Prior efforts have shown that under certain situations retrieval effectiveness may be improved via the use of data fusion techniques. Although these improvements have been observed from the fusion of result sets from several distinct information retrieval systems, it has often been thought that fusing different document retrieval strategies in a single information retrieval system will lead to similar improvements. In this study, we show that this is not the case. We hold constant systemic differences such as parsing, stemming, phrase processing, and relevance feedback, and fuse result sets generated from highly effective retrieval strategies in the same information retrieval system. From this, we show that data fusion of highly effective retrieval strategies alone shows little or no improvement in retrieval effectiveness. Furthermore, we present a detailed analysis of the performance of modern data fusion approaches, and demonstrate the reasons why they do not perform well when applied to this problem. Detailed results and analyses are included to support our conclusions.
Url:
DOI: 10.1002/asi.20012
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 003514
- to stream Istex, to step Curation: 002953
- to stream Istex, to step Checkpoint: 000925
- to stream Main, to step Merge: 000A05
- to stream Main, to step Curation: 000996
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Fusion of effective retrieval strategies in the same information retrieval system</title><author><name sortKey="Beitzel, Steven M" sort="Beitzel, Steven M" uniqKey="Beitzel S" first="Steven M." last="Beitzel">Steven M. Beitzel</name></author><author><name sortKey="Jensen, Eric C" sort="Jensen, Eric C" uniqKey="Jensen E" first="Eric C." last="Jensen">Eric C. Jensen</name></author><author><name sortKey="Chowdhury, Abdur" sort="Chowdhury, Abdur" uniqKey="Chowdhury A" first="Abdur" last="Chowdhury">Abdur Chowdhury</name></author><author><name sortKey="Grossman, David" sort="Grossman, David" uniqKey="Grossman D" first="David" last="Grossman">David Grossman</name></author><author><name sortKey="Frieder, Ophir" sort="Frieder, Ophir" uniqKey="Frieder O" first="Ophir" last="Frieder">Ophir Frieder</name></author><author><name sortKey="Goharian, Nazli" sort="Goharian, Nazli" uniqKey="Goharian N" first="Nazli" last="Goharian">Nazli Goharian</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:CD8B0B2E90A408AA1F7961A80D5D8523F597404B</idno><date when="2004" year="2004">2004</date><idno type="doi">10.1002/asi.20012</idno><idno type="url">https://api.istex.fr/ark:/67375/WNG-74KHTJQK-K/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">003514</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">003514</idno><idno type="wicri:Area/Istex/Curation">002953</idno><idno type="wicri:Area/Istex/Checkpoint">000925</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000925</idno><idno type="wicri:doubleKey">1532-2882:2004:Beitzel S:fusion:of:effective</idno><idno type="wicri:Area/Main/Merge">000A05</idno><idno type="wicri:Area/Main/Curation">000996</idno><idno type="wicri:Area/Main/Exploration">000996</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Fusion of effective retrieval strategies in the same information retrieval system</title><author><name sortKey="Beitzel, Steven M" sort="Beitzel, Steven M" uniqKey="Beitzel S" first="Steven M." last="Beitzel">Steven M. Beitzel</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Jensen, Eric C" sort="Jensen, Eric C" uniqKey="Jensen E" first="Eric C." last="Jensen">Eric C. Jensen</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Chowdhury, Abdur" sort="Chowdhury, Abdur" uniqKey="Chowdhury A" first="Abdur" last="Chowdhury">Abdur Chowdhury</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Grossman, David" sort="Grossman, David" uniqKey="Grossman D" first="David" last="Grossman">David Grossman</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Frieder, Ophir" sort="Frieder, Ophir" uniqKey="Frieder O" first="Ophir" last="Frieder">Ophir Frieder</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author><author><name sortKey="Goharian, Nazli" sort="Goharian, Nazli" uniqKey="Goharian N" first="Nazli" last="Goharian">Nazli Goharian</name><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><placeName><region type="state">Illinois</region></placeName><wicri:cityArea>Information Retrieval Laboratory, Illinois Institute of Technology, Chicago</wicri:cityArea></affiliation><affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country></affiliation></author></analytic><monogr></monogr><series><title level="j" type="main">Journal of the American Society for Information Science and Technology</title><title level="j" type="sub">Document Search Interface Design for Large‐Scale Collections</title><title level="j" type="alt">JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY</title><idno type="ISSN">1532-2882</idno><idno type="eISSN">1532-2890</idno><imprint><biblScope unit="vol">55</biblScope><biblScope unit="issue">10</biblScope><biblScope unit="page" from="859">859</biblScope><biblScope unit="page" to="868">868</biblScope><biblScope unit="page-count">10</biblScope><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>Hoboken</pubPlace><date type="published" when="2004-08">2004-08</date></imprint><idno type="ISSN">1532-2882</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1532-2882</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Algorithm</term><term>American society</term><term>Annual text retrieval conference nist</term><term>Aslam</term><term>Average number</term><term>Average precision</term><term>Best trec systems</term><term>Chowdhury</term><term>Combmnz</term><term>Component result</term><term>Component result sets</term><term>Component sets</term><term>Component systems</term><term>Data fusion</term><term>Data fusion techniques</term><term>Different document retrieval strategies</term><term>Different query representations</term><term>Different retrieval strategies</term><term>Different systems</term><term>Document</term><term>Document analysis</term><term>Effective result sets</term><term>Effective retrieval strategies</term><term>Effective strategies</term><term>Effectiveness improvements</term><term>Frieder</term><term>Fusion</term><term>Fusion techniques</term><term>Future work</term><term>Grossman</term><term>High rank</term><term>High ranks</term><term>Information retrieval</term><term>Information retrieval systems</term><term>Information science</term><term>Knowledge management</term><term>Large number</term><term>Montague</term><term>Multiple pieces</term><term>Other factors</term><term>Overlap</term><term>Overlap analysis</term><term>Overlap correlation</term><term>Overlap hypothesis</term><term>Phrase processing</term><term>Poor indicator</term><term>Query</term><term>Query representations</term><term>Rank displacement</term><term>Relevance feedback</term><term>Relevant documents</term><term>Relevant overlap</term><term>Result sets</term><term>Retrieval</term><term>Retrieval effectiveness</term><term>Retrieval strategies</term><term>Retrieval strategy</term><term>Same information retrieval system</term><term>Same system</term><term>Sigir</term><term>Systemic differences</term><term>Trec</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Prior efforts have shown that under certain situations retrieval effectiveness may be improved via the use of data fusion techniques. Although these improvements have been observed from the fusion of result sets from several distinct information retrieval systems, it has often been thought that fusing different document retrieval strategies in a single information retrieval system will lead to similar improvements. In this study, we show that this is not the case. We hold constant systemic differences such as parsing, stemming, phrase processing, and relevance feedback, and fuse result sets generated from highly effective retrieval strategies in the same information retrieval system. From this, we show that data fusion of highly effective retrieval strategies alone shows little or no improvement in retrieval effectiveness. Furthermore, we present a detailed analysis of the performance of modern data fusion approaches, and demonstrate the reasons why they do not perform well when applied to this problem. Detailed results and analyses are included to support our conclusions.</div></front></TEI><affiliations><list><country><li>États-Unis</li></country><region><li>Illinois</li></region></list><tree><country name="États-Unis"><noRegion><name sortKey="Beitzel, Steven M" sort="Beitzel, Steven M" uniqKey="Beitzel S" first="Steven M." last="Beitzel">Steven M. Beitzel</name></noRegion><name sortKey="Beitzel, Steven M" sort="Beitzel, Steven M" uniqKey="Beitzel S" first="Steven M." last="Beitzel">Steven M. Beitzel</name><name sortKey="Beitzel, Steven M" sort="Beitzel, Steven M" uniqKey="Beitzel S" first="Steven M." last="Beitzel">Steven M. Beitzel</name><name sortKey="Chowdhury, Abdur" sort="Chowdhury, Abdur" uniqKey="Chowdhury A" first="Abdur" last="Chowdhury">Abdur Chowdhury</name><name sortKey="Chowdhury, Abdur" sort="Chowdhury, Abdur" uniqKey="Chowdhury A" first="Abdur" last="Chowdhury">Abdur Chowdhury</name><name sortKey="Chowdhury, Abdur" sort="Chowdhury, Abdur" uniqKey="Chowdhury A" first="Abdur" last="Chowdhury">Abdur Chowdhury</name><name sortKey="Frieder, Ophir" sort="Frieder, Ophir" uniqKey="Frieder O" first="Ophir" last="Frieder">Ophir Frieder</name><name sortKey="Frieder, Ophir" sort="Frieder, Ophir" uniqKey="Frieder O" first="Ophir" last="Frieder">Ophir Frieder</name><name sortKey="Frieder, Ophir" sort="Frieder, Ophir" uniqKey="Frieder O" first="Ophir" last="Frieder">Ophir Frieder</name><name sortKey="Goharian, Nazli" sort="Goharian, Nazli" uniqKey="Goharian N" first="Nazli" last="Goharian">Nazli Goharian</name><name sortKey="Goharian, Nazli" sort="Goharian, Nazli" uniqKey="Goharian N" first="Nazli" last="Goharian">Nazli Goharian</name><name sortKey="Goharian, Nazli" sort="Goharian, Nazli" uniqKey="Goharian N" first="Nazli" last="Goharian">Nazli Goharian</name><name sortKey="Grossman, David" sort="Grossman, David" uniqKey="Grossman D" first="David" last="Grossman">David Grossman</name><name sortKey="Grossman, David" sort="Grossman, David" uniqKey="Grossman D" first="David" last="Grossman">David Grossman</name><name sortKey="Grossman, David" sort="Grossman, David" uniqKey="Grossman D" first="David" last="Grossman">David Grossman</name><name sortKey="Jensen, Eric C" sort="Jensen, Eric C" uniqKey="Jensen E" first="Eric C." last="Jensen">Eric C. Jensen</name><name sortKey="Jensen, Eric C" sort="Jensen, Eric C" uniqKey="Jensen E" first="Eric C." last="Jensen">Eric C. Jensen</name><name sortKey="Jensen, Eric C" sort="Jensen, Eric C" uniqKey="Jensen E" first="Eric C." last="Jensen">Eric C. Jensen</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Informatique/explor/SgmlV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000996 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000996 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Informatique
|area= SgmlV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:CD8B0B2E90A408AA1F7961A80D5D8523F597404B
|texte= Fusion of effective retrieval strategies in the same information retrieval system
}}
| This area was generated with Dilib version V0.6.33. |  |