{"id":"https://openalex.org/W3180230246","doi":"https://doi.org/10.1145/3404835.3463238","title":"Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations","display_name":"Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3180230246","doi":"https://doi.org/10.1145/3404835.3463238","mag":"3180230246"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404835.3463238","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 44th 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://dl.acm.org/doi/pdf/10.1145/3404835.3463238","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"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"]}]},{"author_position":"middle","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":false,"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/A5032699557","display_name":"Sheng-Chieh Lin","orcid":"https://orcid.org/0000-0002-7989-9703"},"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":"Sheng-Chieh 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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014519159","display_name":"Jheng-Hong Yang","orcid":"https://orcid.org/0000-0001-5469-312X"},"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":"Jheng-Hong Yang","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/A5101480198","display_name":"Ronak Pradeep","orcid":"https://orcid.org/0000-0001-6296-601X"},"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":"Ronak Pradeep","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":"last","author":{"id":"https://openalex.org/A5030647281","display_name":"Rodrigo Nogueira","orcid":"https://orcid.org/0000-0002-2600-6035"},"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":"Rodrigo Nogueira","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":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082997975"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":17.7712,"has_fulltext":true,"cited_by_count":315,"citation_normalized_percentile":{"value":0.99762614,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2356","last_page":"2362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9854999780654907,"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":0.9667999744415283,"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/python","display_name":"Python (programming language)","score":0.8741871118545532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8377732634544373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6647902727127075},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5688714981079102},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5160095691680908},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4720607399940491},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34815043210983276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1884576380252838}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8741871118545532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377732634544373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6647902727127075},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5688714981079102},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5160095691680908},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4720607399940491},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34815043210983276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1884576380252838},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3463238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404835.3463238","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 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3404835.3463238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3404835.3463238","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 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"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/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3180230246.pdf","grobid_xml":"https://content.openalex.org/works/W3180230246.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W2000431947","https://openalex.org/W2091379987","https://openalex.org/W2096937925","https://openalex.org/W2287148974","https://openalex.org/W2307814545","https://openalex.org/W2593864460","https://openalex.org/W2740321901","https://openalex.org/W2899154813","https://openalex.org/W2937036051","https://openalex.org/W2951534261","https://openalex.org/W2953384591","https://openalex.org/W2963469388","https://openalex.org/W2965843218","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W2982596739","https://openalex.org/W3001344098","https://openalex.org/W3001879867","https://openalex.org/W3015786360","https://openalex.org/W3021397474","https://openalex.org/W3030698044","https://openalex.org/W3034361442","https://openalex.org/W3036290069","https://openalex.org/W3038572442","https://openalex.org/W3039677769","https://openalex.org/W3045745713","https://openalex.org/W3091207065","https://openalex.org/W3092952717","https://openalex.org/W3093955333","https://openalex.org/W3094297635","https://openalex.org/W3099700870","https://openalex.org/W3102925513","https://openalex.org/W3104914963","https://openalex.org/W3153794000","https://openalex.org/W3154793975","https://openalex.org/W4214484423","https://openalex.org/W4236912465","https://openalex.org/W4285719527","https://openalex.org/W4288089799","https://openalex.org/W6600263792","https://openalex.org/W6603490806","https://openalex.org/W6636625392"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W1582950852","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W2188981919"],"abstract_inverted_index":{"Pyserini":[0,81],"is":[1,32],"a":[2,26,35,136],"Python":[3,37],"toolkit":[4,31,114],"for":[5,50],"reproducible":[6],"information":[7],"retrieval":[8,24,84,92,103],"research":[9,67],"with":[10,41,75],"sparse":[11,83],"and":[12,21,39,47,116,143],"dense":[13,91],"representations.":[14],"It":[15],"aims":[16],"to":[17,59],"provide":[18],"effective,":[19],"reproducible,":[20],"easy-to-use":[22],"first-stage":[23],"in":[25],"multi-stage":[27],"ranking":[28,74,127],"architecture.":[29],"Our":[30],"self-contained":[33],"as":[34,99,101],"standard":[36],"package":[38],"comes":[40],"queries,":[42],"relevance":[43],"judgments,":[44],"pre-built":[45],"indexes,":[46],"evaluation":[48],"scripts":[49],"many":[51],"commonly":[52],"used":[53],"IR":[54],"test":[55],"collections.":[56],"We":[57],"aim":[58],"support,":[60],"out":[61],"of":[62,69,113,138],"the":[63,65],"box,":[64],"entire":[66],"lifecycle":[68],"efforts":[70],"aimed":[71],"at":[72],"improving":[73],"modern":[76],"neural":[77],"approaches.":[78,107],"In":[79],"particular,":[80],"supports":[82],"(e.g.,":[85,93],"BM25":[86],"scoring":[87],"using":[88],"bag-of-words":[89],"representations),":[90,98],"nearest-neighbor":[94],"search":[95],"on":[96,124],"transformer-encoded":[97],"well":[100],"hybrid":[102],"that":[104,120,145],"integrates":[105],"both":[106],"This":[108],"paper":[109],"provides":[110],"an":[111],"overview":[112],"features":[115],"presents":[117],"empirical":[118],"results":[119],"illustrate":[121],"its":[122],"effectiveness":[123],"two":[125],"popular":[126],"tasks.":[128],"Around":[129],"this":[130],"toolkit,":[131],"our":[132],"group":[133],"has":[134],"built":[135],"culture":[137],"reproducibility":[139],"through":[140],"shared":[141],"norms":[142],"tools":[144],"enable":[146],"rigorous":[147],"automated":[148],"testing.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":71},{"year":2024,"cited_by_count":57},{"year":2023,"cited_by_count":101},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}