{"id":"https://openalex.org/W2042980227","doi":"https://doi.org/10.1145/1148170.1148204","title":"LDA-based document models for ad-hoc retrieval","display_name":"LDA-based document models for ad-hoc retrieval","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2042980227","doi":"https://doi.org/10.1145/1148170.1148204","mag":"2042980227"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040886197","display_name":"Xing Wei","orcid":"https://orcid.org/0000-0002-5025-3941"},"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":"Xing Wei","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, 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, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040886197"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":60.4769,"has_fulltext":false,"cited_by_count":1084,"citation_normalized_percentile":{"value":0.99936457,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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":0.9865999817848206,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8837792277336121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8386684060096741},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6582752466201782},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.6345534920692444},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6290422677993774},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6002304553985596},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.549785315990448},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5249750018119812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48506322503089905},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35650989413261414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3350450396537781}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8837792277336121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386684060096741},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6582752466201782},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.6345534920692444},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6290422677993774},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6002304553985596},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.549785315990448},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5249750018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48506322503089905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35650989413261414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3350450396537781},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1148170.1148204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:18911","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:18911","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:alma.61RMIT_INST:11246519140001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/1148170.1148204","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27376011","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27376011","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2020999234","https://openalex.org/W2062270497","https://openalex.org/W2063397738","https://openalex.org/W2093390569","https://openalex.org/W2106490775","https://openalex.org/W2107668593","https://openalex.org/W2107743791","https://openalex.org/W2112971401","https://openalex.org/W2124434590","https://openalex.org/W2130395434","https://openalex.org/W2132827946","https://openalex.org/W2136542423","https://openalex.org/W2140124448","https://openalex.org/W2147152072","https://openalex.org/W2150286230","https://openalex.org/W2158266063","https://openalex.org/W2160746453","https://openalex.org/W2169213601","https://openalex.org/W2595697910","https://openalex.org/W4206765718","https://openalex.org/W4233135949","https://openalex.org/W4240913316","https://openalex.org/W4245107743","https://openalex.org/W4246858749","https://openalex.org/W6650793866"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4291700620","https://openalex.org/W2352674739"],"abstract_inverted_index":{"Search":[0],"algorithms":[1],"incorporating":[2],"some":[3],"form":[4],"of":[5,48],"topic":[6,40],"model":[7,34,47,92],"have":[8],"a":[9,44],"long":[10],"history":[11],"in":[12,31,57,67,113],"information":[13,68],"retrieval.":[14,86],"For":[15],"example,":[16],"cluster-based":[17,128],"retrieval":[18,69,126],"has":[19,26],"been":[20],"studied":[21],"since":[22],"the":[23,32,58,94,116],"60s":[24],"and":[25,65,98,115],"recently":[27],"produced":[28],"good":[29],"results":[30],"language":[33,95],"framework.":[35],"An":[36],"approach":[37],"to":[38,79,83,109],"building":[39],"models":[41,129],"based":[42],"on":[43,101],"formal":[45],"generative":[46],"documents,":[49],"Latent":[50],"Dirichlet":[51],"Allocation":[52],"(LDA),":[53],"is":[54,70,107,119],"heavily":[55],"cited":[56],"machine":[59],"learning":[60],"literature,":[61],"but":[62],"its":[63],"feasibility":[64],"effectiveness":[66],"mostly":[71],"unknown.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"study":[77],"how":[78],"efficiently":[80],"use":[81],"LDA":[82,114],"improve":[84],"ad-hoc":[85],"We":[87,121],"propose":[88],"an":[89],"LDA-based":[90],"document":[91],"within":[93],"modeling":[96],"framework,":[97],"evaluate":[99],"it":[100],"several":[102],"TREC":[103],"collections.":[104],"Gibbs":[105],"sampling":[106],"employed":[108],"conduct":[110],"approximate":[111],"inference":[112],"computational":[117],"complexity":[118],"analyzed.":[120],"show":[122],"that":[123],"improvements":[124],"over":[125],"using":[127],"can":[130],"be":[131],"obtained":[132],"with":[133],"reasonable":[134],"efficiency.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":52},{"year":2019,"cited_by_count":64},{"year":2018,"cited_by_count":73},{"year":2017,"cited_by_count":84},{"year":2016,"cited_by_count":77},{"year":2015,"cited_by_count":96},{"year":2014,"cited_by_count":71},{"year":2013,"cited_by_count":83},{"year":2012,"cited_by_count":79}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}