{"id":"https://openalex.org/W3194206959","doi":"https://doi.org/10.1145/3459637.3482156","title":"On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval","display_name":"On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3194206959","doi":"https://doi.org/10.1145/3459637.3482156","mag":"3194206959"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.11480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Craig Macdonald","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nicola Tonellotto","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":1.1199,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82412419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3318","last_page":"3322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9987000226974487,"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/ranking","display_name":"Ranking (information retrieval)","score":0.8234000205993652},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6574000120162964},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5037000179290771},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4503999948501587},{"id":"https://openalex.org/keywords/nearest-neighbour","display_name":"Nearest neighbour","score":0.4404999911785126}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8234000205993652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718000173568726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6032999753952026},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5037000179290771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724999964237213},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C2983946233","wikidata":"https://www.wikidata.org/wiki/Q4088109","display_name":"Nearest neighbour","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3459637.3482156","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.11480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.11480","pdf_url":"https://arxiv.org/pdf/2108.11480","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.gla.ac.uk:249263","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/3545.html>","pdf_url":"https://eprints.gla.ac.uk/249263/3/249263.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arpi.unipi.it:11568/1114336","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/1114336","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.11480","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.11480","pdf_url":"https://arxiv.org/pdf/2108.11480","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1989121949","display_name":null,"funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5187265158","display_name":"Closed-Loop Data Science for Complex, Computationally- and Data-Intensive Analytics","funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G75858821","display_name":null,"funder_award_id":"CrossLab","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G8091430692","display_name":null,"funder_award_id":"(MIUR)","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"},{"id":"https://openalex.org/G8352026019","display_name":null,"funder_award_id":"R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320317295","display_name":"Dipartimenti di Eccellenza","ror":null},{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2007815473","https://openalex.org/W2053448995","https://openalex.org/W2096937925","https://openalex.org/W2940927814","https://openalex.org/W2953774736","https://openalex.org/W3021397474","https://openalex.org/W3021779606","https://openalex.org/W3023238803","https://openalex.org/W3045745713","https://openalex.org/W3094476882","https://openalex.org/W3099700870","https://openalex.org/W3136109765","https://openalex.org/W3150521056","https://openalex.org/W3194741792","https://openalex.org/W3209981429"],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrieval,":[1],"which":[2,74],"describes":[3],"the":[4,51,54,97,100,107,114,121,132,142,147],"use":[5,108],"of":[6,33,53,67,88,99,109,123,141],"contextualised":[7],"language":[8],"models":[9],"such":[10],"as":[11],"BERT":[12],"to":[13,63,119,150],"identify":[14,64],"documents":[15,40,69,89,125],"from":[16],"a":[17,65,85,170],"collection":[18],"by":[19,45,139,145],"leveraging":[20],"approximate":[21,61,148],"nearest":[22],"neighbour":[23],"(ANN)":[24],"techniques,":[25],"has":[26],"been":[27],"increasing":[28],"in":[29,117,165,169,173],"popularity.":[30],"Two":[31],"families":[32],"approaches":[34],"have":[35],"emerged,":[36],"depending":[37],"on":[38,131],"whether":[39],"and":[41,60,167],"queries":[42],"are":[43,75],"represented":[44],"single":[46],"or":[47],"multiple":[48],"embeddings.":[49],"ColBERT,":[50],"exemplar":[52],"latter,":[55],"uses":[56],"an":[57,158],"ANN":[58,110],"index":[59],"scores":[62,111,149],"set":[66,144],"candidate":[68,115,124,143],"for":[70,93,112],"each":[71,94],"query":[72],"embedding,":[73],"then":[76],"re-ranked":[77],"using":[78,146],"accurate":[79],"document":[80],"representations.":[81],"In":[82,102],"this":[83,103],"manner,":[84],"large":[86],"number":[87,122],"can":[90,155],"be":[91],"retrieved":[92],"query,":[95],"hindering":[96],"efficiency":[98],"approach.":[101],"work,":[104],"we":[105,154],"investigate":[106],"ranking":[113,135,160],"documents,":[116,153],"order":[118],"decrease":[120],"being":[126],"fully":[127],"scored.":[128],"Experiments":[129],"conducted":[130],"MSMARCO":[133],"passage":[134],"corpus":[136],"demonstrate":[137],"that,":[138],"cutting":[140],"only":[151],"200":[152],"still":[156],"obtain":[157],"effective":[159],"without":[161],"statistically":[162],"significant":[163],"differences":[164],"effectiveness,":[166],"resulting":[168],"2x":[171],"speedup":[172],"efficiency.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2021-08-30T00:00:00"}