{"id":"https://openalex.org/W4387846582","doi":"https://doi.org/10.1145/3583780.3615112","title":"Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes","display_name":"Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387846582","doi":"https://doi.org/10.1145/3583780.3615112"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","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/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083417786","display_name":"Tommaso Teofili","orcid":"https://orcid.org/0000-0002-4372-0273"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Teofili","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021623012"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.7469,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8585406,"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":"5366","last_page":"5370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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":0.8238118886947632},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7041370868682861},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6042671203613281},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4605414569377899},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4277645945549011},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4250493049621582},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1940845251083374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238118886947632},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7041370868682861},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6042671203613281},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4605414569377899},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4277645945549011},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4250493049621582},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1940845251083374},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2740321901","https://openalex.org/W2962985038","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W2999905431","https://openalex.org/W3099700870","https://openalex.org/W3168875417","https://openalex.org/W3172119680","https://openalex.org/W3180230246","https://openalex.org/W3184918446","https://openalex.org/W3211670924","https://openalex.org/W4213045215","https://openalex.org/W4226208814","https://openalex.org/W4252076394","https://openalex.org/W4256565756","https://openalex.org/W4284682639","https://openalex.org/W4384823501"],"related_works":["https://openalex.org/W3001245047","https://openalex.org/W1873153460","https://openalex.org/W850316024","https://openalex.org/W2170059263","https://openalex.org/W2044231962","https://openalex.org/W2945915803","https://openalex.org/W2969770061","https://openalex.org/W301348785","https://openalex.org/W2117230983","https://openalex.org/W4390861283"],"abstract_inverted_index":{"Anserini":[0,158],"is":[1],"a":[2,48,78,132],"Lucene-based":[3],"toolkit":[4],"for":[5,24,116,171],"reproducible":[6],"information":[7],"retrieval":[8,22,28,36,61,91,130,173],"research":[9],"in":[10,17,77,120,141],"Java":[11],"that":[12,86,156],"has":[13],"been":[14],"gaining":[15],"traction":[16],"the":[18,68,111,123,142,148],"community.":[19],"It":[20],"provides":[21,47],"capabilities":[23],"both":[25,57,126],"\"traditional\"":[26],"bag-of-words":[27],"models":[29,92],"such":[30,41],"as":[31,33,35,42,63],"BM25":[32],"well":[34],"using":[37,175],"learned":[38],"sparse":[39,58,88,129],"representations":[40],"SPLADE.":[43],"With":[44],"Pyserini,":[45],"which":[46,104],"Python":[49],"interface":[50],"to":[51,56,67,94],"Anserini,":[52],"users":[53],"gain":[54],"access":[55],"and":[59,89,108,128,152,164],"dense":[60,90,117,127,172],"models,":[62,174],"Pyserini":[64],"implements":[65],"bindings":[66],"Faiss":[69],"vector":[70,118],"search":[71,119,170],"library":[72],"alongside":[73],"Lucene":[74,121],"inverted":[75],"indexes":[76,115],"uniform,":[79],"consistent":[80],"interface.":[81],"Nevertheless,":[82],"hybrid":[83],"fusion":[84],"techniques":[85],"integrate":[87],"need":[93],"stitch":[95],"together":[96],"results":[97],"from":[98],"two":[99],"completely":[100],"different":[101],"\"software":[102],"stacks\",":[103],"creates":[105],"unnecessary":[106],"complexities":[107],"inefficiencies.":[109],"However,":[110],"introduction":[112],"of":[113,125,144],"HNSW":[114,159],"promises":[122],"integration":[124,140,160],"within":[131],"single":[133],"software":[134],"framework.":[135],"We":[136],"explore":[137],"exactly":[138],"this":[139],"context":[143],"Anserini.":[145],"Experiments":[146],"on":[147],"MS":[149],"MARCO":[150],"passage":[151],"BEIR":[153],"datasets":[154],"show":[155],"our":[157],"supports":[161],"(reasonably)":[162,165],"effective":[163],"efficient":[166],"approximate":[167],"nearest":[168],"neighbor":[169],"only":[176],"Lucene.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}