{"id":"https://openalex.org/W2130395434","doi":"https://doi.org/10.1145/1008992.1009026","title":"Cluster-based retrieval using language models","display_name":"Cluster-based retrieval using language models","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2130395434","doi":"https://doi.org/10.1145/1008992.1009026","mag":"2130395434"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100707681","display_name":"Xiaoyong Liu","orcid":"https://orcid.org/0000-0001-7085-5440"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoyong Liu","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105659698","display_name":"W. Bruce Croft","orcid":"https://orcid.org/0000-0003-2391-9629"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100707681"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":58.9455,"has_fulltext":false,"cited_by_count":449,"citation_normalized_percentile":{"value":0.99861813,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324599266052246},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7531360983848572},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7289407253265381},{"id":"https://openalex.org/keywords/human\u2013computer-information-retrieval","display_name":"Human\u2013computer information retrieval","score":0.5846901535987854},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5715506076812744},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5565871596336365},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.47102031111717224},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4637065529823303},{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.461978554725647},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.44858384132385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3039708435535431},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.2671145796775818},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.24621424078941345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324599266052246},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7531360983848572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7289407253265381},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.5846901535987854},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5715506076812744},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5565871596336365},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.47102031111717224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4637065529823303},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.461978554725647},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.44858384132385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3039708435535431},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2671145796775818},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.24621424078941345},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1008992.1009026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.83.4177","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.83.4177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir.cs.umass.edu/pubfiles/ir-347.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W514365","https://openalex.org/W66569044","https://openalex.org/W1519852910","https://openalex.org/W1592059639","https://openalex.org/W1614151208","https://openalex.org/W1904228841","https://openalex.org/W1981825277","https://openalex.org/W1990388042","https://openalex.org/W2004545875","https://openalex.org/W2041565863","https://openalex.org/W2045584315","https://openalex.org/W2061198046","https://openalex.org/W2065938637","https://openalex.org/W2074449313","https://openalex.org/W2084048649","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2100506586","https://openalex.org/W2102270039","https://openalex.org/W2114804204","https://openalex.org/W2135909747","https://openalex.org/W2145036943","https://openalex.org/W2153252192","https://openalex.org/W2155194165","https://openalex.org/W2162746367","https://openalex.org/W2169213601","https://openalex.org/W2608050011","https://openalex.org/W4206765718","https://openalex.org/W4238437991","https://openalex.org/W4244975643","https://openalex.org/W4246858749","https://openalex.org/W4252060112","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W166528628","https://openalex.org/W2385640135","https://openalex.org/W2378891848","https://openalex.org/W1484057680","https://openalex.org/W3154610306","https://openalex.org/W188831073","https://openalex.org/W2046983134","https://openalex.org/W2041565863","https://openalex.org/W168472812","https://openalex.org/W2130395434"],"abstract_inverted_index":{"Previous":[0],"research":[1],"on":[2,52],"cluster-based":[3,47,59],"retrieval":[4,15,39,48,60,74],"has":[5],"been":[6],"inconclusive":[7],"as":[8],"to":[9,27,32],"whether":[10],"it":[11],"does":[12],"bring":[13],"improved":[14],"effectiveness":[16],"over":[17,72],"document-based":[18,73],"retrieval.":[19],"Recent":[20],"developments":[21],"in":[22,78],"the":[23],"language":[24],"modeling":[25],"approach":[26],"IR":[28],"have":[29],"motivated":[30],"us":[31],"re-examine":[33],"this":[34,37],"problem":[35],"within":[36],"new":[38,44],"framework.":[40],"We":[41,56],"propose":[42],"two":[43],"models":[45],"for":[46],"and":[49,69,83],"evaluate":[50],"them":[51],"several":[53],"TREC":[54],"collections.":[55],"show":[57],"that":[58],"can":[61,75],"perform":[62],"consistently":[63],"across":[64],"collections":[65],"of":[66],"realistic":[67],"size,":[68],"significant":[70],"improvements":[71],"be":[76],"obtained":[77],"a":[79],"fully":[80],"automatic":[81],"manner":[82],"without":[84],"relevance":[85],"information":[86],"provided":[87],"by":[88],"human.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":35}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}