{"id":"https://openalex.org/W4384828687","doi":"https://doi.org/10.1145/3539618.3591902","title":"SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval","display_name":"SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384828687","doi":"https://doi.org/10.1145/3539618.3591902"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591902","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052977545","display_name":"Nandan Thakur","orcid":"https://orcid.org/0000-0001-6107-2460"},"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":"Nandan Thakur","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6107-2460","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397196","display_name":"Kexin Wang","orcid":"https://orcid.org/0000-0003-1175-7829"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kexin Wang","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1175-7829","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2187-7621","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0002-0661-7189","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052977545"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.6816,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75158444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2964","last_page":"2974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8307563066482544},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.617664635181427},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48191145062446594},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.47877418994903564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4772510230541229},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.47199228405952454},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.46803122758865356},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4384881556034088},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34501153230667114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307563066482544},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.617664635181427},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48191145062446594},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.47877418994903564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772510230541229},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.47199228405952454},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.46803122758865356},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4384881556034088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34501153230667114},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591902","pdf_url":null,"source":null,"license":null,"license_id":null,"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"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:138887","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/138887/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W145388748","https://openalex.org/W1821462560","https://openalex.org/W2065240770","https://openalex.org/W2798658104","https://openalex.org/W2897754576","https://openalex.org/W2937036051","https://openalex.org/W2951434086","https://openalex.org/W2978017171","https://openalex.org/W2980282514","https://openalex.org/W2981852735","https://openalex.org/W2998702515","https://openalex.org/W3034912391","https://openalex.org/W3045745713","https://openalex.org/W3088652013","https://openalex.org/W3090721331","https://openalex.org/W3094297635","https://openalex.org/W3099700870","https://openalex.org/W3099977667","https://openalex.org/W3104894527","https://openalex.org/W3104914963","https://openalex.org/W3130740619","https://openalex.org/W3134665270","https://openalex.org/W3154280800","https://openalex.org/W3154670582","https://openalex.org/W3154755316","https://openalex.org/W3155114168","https://openalex.org/W3156836409","https://openalex.org/W3174203100","https://openalex.org/W3180230246","https://openalex.org/W3193367516","https://openalex.org/W3209946909","https://openalex.org/W4200630182","https://openalex.org/W4226059474","https://openalex.org/W4252076394","https://openalex.org/W4284663260","https://openalex.org/W4286969177","https://openalex.org/W4287645694","https://openalex.org/W4288089799","https://openalex.org/W4297808394","https://openalex.org/W4320855048","https://openalex.org/W4327499170"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Traditionally,":[0],"sparse":[1,29,49,64,82,138,175,202,221,249],"retrieval":[2,16,30,83,101,114,176],"systems":[3,102],"relied":[4],"on":[5,85,89,127,197],"lexical":[6],"representations":[7,222],"to":[8,33,109],"retrieve":[9],"documents,":[10],"such":[11,25],"as":[12,26],"BM25,":[13],"dominated":[14],"information":[15],"tasks.":[17,115],"With":[18],"the":[19,40,179,189,210,230],"onset":[20],"of":[21,78,193,226,229],"pre-trained":[22],"transformer":[23],"models":[24,65,84,104,159],"BERT,":[27],"neural":[28,137,201],"has":[31,43],"led":[32],"a":[34,53,76,90,96,122,132,224,244],"new":[35],"paradigm":[36],"within":[37],"retrieval.":[38,139],"Despite":[39],"success,":[41],"there":[42],"been":[44],"limited":[45],"software":[46],"supporting":[47,131],"different":[48,63],"retrievers":[50],"running":[51],"in":[52,99,260],"unified,":[54],"common":[55,133],"environment.":[56],"This":[57],"hinders":[58],"practitioners":[59],"from":[60],"fairly":[61],"comparing":[62],"and":[66,129,151,172,233,257],"obtaining":[67],"realistic":[68],"evaluation":[69],"results.":[70],"Another":[71],"missing":[72],"piece":[73],"is,":[74],"that":[75,105,186,218],"majority":[77,225],"prior":[79],"work":[80],"evaluates":[81],"in-domain":[86],"retrieval,":[87],"i.e.":[88,112,243],"single":[91],"dataset:":[92],"MS":[93],"MARCO.":[94],"However,":[95],"key":[97],"requirement":[98],"practical":[100],"requires":[103],"can":[106,154],"generalize":[107],"well":[108],"unseen":[110],"out-of-domain,":[111],"zero-shot":[113,174],"In":[116,204],"this":[117,205],"work,":[118,206],"we":[119,169,207],"provide":[120,252],"SPRINT,":[121],"unified":[123],"python":[124],"toolkit":[125,141],"based":[126],"Pyserini":[128],"Lucene,":[130],"interface":[134],"for":[135,239],"evaluating":[136],"The":[140],"currently":[142],"includes":[143],"five":[144],"built-in":[145],"models:":[146],"uniCOIL,":[147],"DeepImpact,":[148],"SPARTA,":[149],"TILDEv2":[150],"SPLADEv2.":[152],"Users":[153],"also":[155],"easily":[156],"add":[157],"customized":[158],"by":[160],"defining":[161],"their":[162],"term":[163],"weighting":[164],"method.":[165],"Using":[166],"our":[167,253,261],"toolkit,":[168,255],"establish":[170],"strong":[171],"reproducible":[173],"baselines":[177],"across":[178],"well-acknowledged":[180],"benchmark,":[181],"BEIR.":[182],"Our":[183],"results":[184],"demonstrate":[185],"SPLADEv2":[187,219],"achieves":[188],"best":[190],"average":[191],"score":[192],"0.470":[194],"[email":[195],"protected]":[196],"BEIR":[198],"amongst":[199],"all":[200],"retrievers.":[203],"further":[208],"uncover":[209],"reasons":[211],"behind":[212],"its":[213,240,247],"performance":[214,241],"gain.":[215],"We":[216,251],"show":[217],"produces":[220],"with":[223],"tokens":[227],"outside":[228],"original":[231],"query":[232],"document":[234],"which":[235],"is":[236],"often":[237],"crucial":[238],"gains,":[242],"limitation":[245],"among":[246],"other":[248],"counterparts.":[250],"SPRINT":[254],"models,":[256],"data":[258],"used":[259],"experiments":[262],"publicly":[263],"here:":[264],"https://github.com/thakur-nandan/sprint.":[265]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}