{"id":"https://openalex.org/W3200660033","doi":"https://doi.org/10.1145/3459637.3482159","title":"Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection","display_name":"Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3200660033","doi":"https://doi.org/10.1145/3459637.3482159","mag":"3200660033"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482159","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.10739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049487742","display_name":"Negar Arabzadeh","orcid":"https://orcid.org/0000-0002-4411-7089"},"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":"Negar Arabzadeh","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101018904","display_name":"Xinyi Yan","orcid":null},"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":"Xinyi Yan","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"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":"Charles L. A. Clarke","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada","University of Waterloo Waterloo, ON Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo Waterloo, ON Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049487742"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13512296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2862","last_page":"2866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9930999875068665,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9797999858856201,"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":0.7853485941886902},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.535304605960846},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5221855044364929},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43339940905570984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3733123242855072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853485941886902},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.535304605960846},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5221855044364929},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43339940905570984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3733123242855072}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3459637.3482159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482159","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:2109.10739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.10739","pdf_url":"https://arxiv.org/pdf/2109.10739","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":"mag:3200660033","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2109.10739.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2109.10739","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.10739","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.10739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.10739","pdf_url":"https://arxiv.org/pdf/2109.10739","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":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3200660033.pdf","grobid_xml":"https://content.openalex.org/works/W3200660033.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2068905009","https://openalex.org/W2153252192","https://openalex.org/W2154610494","https://openalex.org/W2740321901","https://openalex.org/W2896457183","https://openalex.org/W2909544278","https://openalex.org/W2938224028","https://openalex.org/W2953774736","https://openalex.org/W2970641574","https://openalex.org/W2980708516","https://openalex.org/W2982596739","https://openalex.org/W2998702515","https://openalex.org/W3004654429","https://openalex.org/W3017018726","https://openalex.org/W3021282678","https://openalex.org/W3021397474","https://openalex.org/W3022373106","https://openalex.org/W3037128914","https://openalex.org/W3038572442","https://openalex.org/W3044284384","https://openalex.org/W3091406553","https://openalex.org/W3092683697","https://openalex.org/W3093955333","https://openalex.org/W4243333943","https://openalex.org/W4252060112"],"related_works":["https://openalex.org/W3210436917","https://openalex.org/W3154670582","https://openalex.org/W3173989853","https://openalex.org/W2343765202","https://openalex.org/W2922877887","https://openalex.org/W3209791570","https://openalex.org/W2285329326","https://openalex.org/W3207689594","https://openalex.org/W3136914084","https://openalex.org/W2979894627","https://openalex.org/W3094012830","https://openalex.org/W2003046692","https://openalex.org/W2949719529","https://openalex.org/W3112177522","https://openalex.org/W3016011575","https://openalex.org/W2613883163","https://openalex.org/W2968985048","https://openalex.org/W2070299948","https://openalex.org/W3045653366","https://openalex.org/W2950808778"],"abstract_inverted_index":{"Over":[0],"the":[1,38,136,151,192,233,240],"last":[2],"few":[3],"years,":[4],"contextualized":[5,54],"pre-trained":[6,45],"transformer":[7,46],"models":[8,47],"such":[9,24,48],"as":[10,25,49],"BERT":[11],"have":[12,103],"provided":[13],"substantial":[14,68,81],"improvements":[15,71],"on":[16,28,44,232,239,269],"information":[17,109],"retrieval":[18,22,69,168,229,259],"tasks.":[19],"Traditional":[20],"sparse":[21,74,101,128,156,171,180,189,226],"methods":[23],"BM25":[26],"rely":[27],"high-dimensional,":[29],"sparse,":[30,254],"bag-of-words":[31],"query":[32,140,203,234],"representations":[33,55],"to":[34,73,89,106,112,116,134,164,196,265],"retrieve":[35,107],"documents.":[36,142],"On":[37],"other":[39],"hand,":[40],"recent":[41],"approaches":[42],"based":[43,127,231,268],"BERT,":[50],"fine-tune":[51],"dense":[52,65,85,113,132,158,173,228,256],"low-dimensional":[53],"of":[56,155,194,249],"queries":[57,183],"and":[58,84,96,141,153,212,227,273],"documents":[59],"in":[60],"embedding":[61],"space.":[62],"While":[63],"these":[64],"retrievers":[66,86,102,123,129,133,159,181,190],"enjoy":[67],"effectiveness":[70],"compared":[72],"retrievers,":[75,114],"they":[76],"are":[77,87],"computationally":[78],"intensive,":[79],"requiring":[80],"GPU":[82],"resources,":[83],"known":[88],"be":[90,186,266],"more":[91],"expensive":[92],"from":[93],"both":[94],"time":[95],"resource":[97,274],"perspectives.":[98],"In":[99,143],"addition,":[100],"been":[104],"shown":[105],"complementary":[108],"with":[110,131,188],"respect":[111],"leading":[115],"proposals":[117],"for":[118,176,182],"hybrid":[119,122,258],"retrievers.":[120],"These":[121],"leverage":[124],"low-cost,":[125],"exact-matching":[126],"along":[130],"bridge":[135],"semantic":[137],"gaps":[138],"between":[139,150,225,252],"this":[144,148],"work,":[145],"we":[146,207,216],"address":[147],"trade-off":[149],"cost":[152],"utility":[154,200],"vs":[157],"by":[160],"proposing":[161],"a":[162,166,270],"classifier":[163,222],"select":[165,224],"suitable":[167],"strategy":[169,264],"(i.e.,":[170],"vs.":[172,174],"hybrid)":[175],"individual":[177],"queries.":[178],"Leveraging":[179],"which":[184],"can":[185,223],"answered":[187],"decreases":[191],"number":[193],"calls":[195],"GPUs.":[197],"Consequently,":[198],"while":[199],"is":[201],"maintained,":[202],"latency":[204,272],"decreases.":[205],"Although":[206],"use":[208],"less":[209,214],"computational":[210],"resources":[211],"spend":[213],"time,":[215],"still":[217],"achieve":[218],"improved":[219,247],"performance.":[220],"Our":[221],"strategies":[230],"alone.":[235],"We":[236],"conduct":[237],"experiments":[238],"MS":[241],"MARCO":[242],"passage":[243],"dataset":[244],"demonstrating":[245],"an":[246,262],"range":[248],"efficiency/effectiveness":[250],"trade-offs":[251],"purely":[253,255],"or":[257],"strategies,":[260],"allowing":[261],"appropriate":[263],"selected":[267],"target":[271],"budget.":[275]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}