{"id":"https://openalex.org/W4384659759","doi":"https://doi.org/10.1145/3539618.3591740","title":"Multivariate Representation Learning for Information Retrieval","display_name":"Multivariate Representation Learning for Information Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384659759","doi":"https://doi.org/10.1145/3539618.3591740"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591740","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th 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":"gold","oa_url":"https://doi.org/10.1145/3539618.3591740","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"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":"Hamed Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101457713"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.2242,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83165383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688542008399963},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.6351802349090576},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6018111109733582},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5840070843696594},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.5558760166168213},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5535967350006104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297749042510986},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48941460251808167},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4404236674308777},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43234074115753174},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4230096638202667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36130577325820923},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35944584012031555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32064366340637207},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.29021942615509033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1323043406009674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688542008399963},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.6351802349090576},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6018111109733582},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5840070843696594},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.5558760166168213},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5535967350006104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297749042510986},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48941460251808167},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4404236674308777},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43234074115753174},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4230096638202667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36130577325820923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35944584012031555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32064366340637207},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29021942615509033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1323043406009674},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591740","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3539618.3591740","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591740","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1577798322","https://openalex.org/W1608396526","https://openalex.org/W1980730196","https://openalex.org/W1999322447","https://openalex.org/W2036181041","https://openalex.org/W2069870183","https://openalex.org/W2079168273","https://openalex.org/W2132314908","https://openalex.org/W2132706284","https://openalex.org/W2146938270","https://openalex.org/W2148933855","https://openalex.org/W2158499994","https://openalex.org/W2165612380","https://openalex.org/W2256784804","https://openalex.org/W2809897079","https://openalex.org/W2897754576","https://openalex.org/W2918071347","https://openalex.org/W2963469388","https://openalex.org/W2963690776","https://openalex.org/W2981852735","https://openalex.org/W2998702515","https://openalex.org/W3015548520","https://openalex.org/W3034912391","https://openalex.org/W3099700870","https://openalex.org/W3099977667","https://openalex.org/W3128581554","https://openalex.org/W3153557349","https://openalex.org/W3154670582","https://openalex.org/W3155895380","https://openalex.org/W3156054180","https://openalex.org/W3168875417","https://openalex.org/W3195010973","https://openalex.org/W3217305727","https://openalex.org/W4206390054","https://openalex.org/W4206765718","https://openalex.org/W4225156005","https://openalex.org/W4229065825","https://openalex.org/W4242973245","https://openalex.org/W4243333943","https://openalex.org/W4288089799","https://openalex.org/W4290943593"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W4389832810","https://openalex.org/W3133533225"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,130,153],"models":[2,94],"use":[3],"bi-encoder":[4],"network":[5],"architectures":[6],"for":[7,45,53,101,109],"learning":[8,43,50],"query":[9,55],"and":[10,24,56,64,78,89,98,113,145],"document":[11],"representations.":[12],"These":[13],"representations":[14],"are":[15,27,86],"often":[16,28],"in":[17],"the":[18,31,72,84,110,122],"form":[19],"of":[20,49,137,143],"a":[21,40,51,61,106,140],"vector":[22,52],"representation":[23,42],"their":[25],"similarities":[26],"computed":[29],"using":[30],"dot":[32],"product":[33],"function.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,81],"propose":[39],"new":[41],"framework":[44,59,112],"dense":[46,152],"retrieval.":[47],"Instead":[48],"each":[54],"document,":[57],"our":[58],"learns":[60],"multivariate":[62,67,87],"distribution":[63],"uses":[65],"negative":[66],"KL":[68],"divergence":[69],"to":[70,95,128,150],"compute":[71],"similarity":[73],"between":[74],"distributions.":[75,103],"For":[76],"simplicity":[77],"efficiency":[79],"reasons,":[80],"assume":[82],"that":[83,115],"distributions":[85],"normals":[88],"then":[90],"train":[91],"large":[92],"language":[93],"produce":[96],"mean":[97],"variance":[99],"vectors":[100],"these":[102],"We":[104,132],"provide":[105],"theoretical":[107],"foundation":[108],"proposed":[111],"show":[114],"it":[116],"can":[117],"be":[118],"seamlessly":[119],"integrated":[120],"into":[121],"existing":[123],"approximate":[124],"nearest":[125],"neighbor":[126],"algorithms":[127],"perform":[129],"efficiently.":[131],"conduct":[133],"an":[134],"extensive":[135],"suite":[136],"experiments":[138],"on":[139],"wide":[141],"range":[142],"datasets,":[144],"demonstrate":[146],"significant":[147],"improvements":[148],"compared":[149],"competitive":[151],"models.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}