{"id":"https://openalex.org/W4284689925","doi":"https://doi.org/10.1145/3477495.3531740","title":"The Istella22 Dataset","display_name":"The Istella22 Dataset","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4284689925","doi":"https://doi.org/10.1145/3477495.3531740"},"language":"en","primary_location":{"id":"doi:10.1145/3477495.3531740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531740","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/268514/1/268514.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018075218","display_name":"Domenico Dato","orcid":"https://orcid.org/0000-0002-3444-2785"},"institutions":[{"id":"https://openalex.org/I2800599128","display_name":"Istituto Superiore Mario Boella","ror":"https://ror.org/05y6jfx28","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800599128","https://openalex.org/I4210155299"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Domenico Dato","raw_affiliation_strings":["Istella, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istella, Milano, Italy","institution_ids":["https://openalex.org/I2800599128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199889","display_name":"Sean MacAvaney","orcid":"https://orcid.org/0000-0002-8914-2659"},"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":false,"raw_author_name":"Sean MacAvaney","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082554104","display_name":"Franco Maria Nardini","orcid":"https://orcid.org/0000-0003-3183-334X"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Maria Nardini","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605298","display_name":"Raffaele Perego","orcid":"https://orcid.org/0000-0001-7189-4724"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Perego","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3099","last_page":"3107"},"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":0.9986000061035156,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.827133297920227},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6877545118331909},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6070188283920288},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5653411746025085},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5613026022911072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463595390319824},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5338550806045532},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5249426364898682},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48522496223449707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4329247772693634},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4319028854370117},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.429836243391037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827133297920227},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6877545118331909},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6070188283920288},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5653411746025085},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5613026022911072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463595390319824},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5338550806045532},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5249426364898682},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48522496223449707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4329247772693634},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4319028854370117},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.429836243391037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3477495.3531740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477495.3531740","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:268514","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60888.html>","pdf_url":"https://eprints.gla.ac.uk/268514/1/268514.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":"Conference Proceedings"},{"id":"pmh:oai:arpi.unipi.it:11568/1163071","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1163071","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"},{"id":"pmh:oai:dnet:people______::98ce4b0e112eb19f1b2be79b1c4ca7d7","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:268514","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60888.html>","pdf_url":"https://eprints.gla.ac.uk/268514/1/268514.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":"Conference Proceedings"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G899169222","display_name":null,"funder_award_id":"871042","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4284689925.pdf","grobid_xml":"https://content.openalex.org/works/W4284689925.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1973435495","https://openalex.org/W1982858363","https://openalex.org/W1990190154","https://openalex.org/W2070299948","https://openalex.org/W2105157020","https://openalex.org/W2109227373","https://openalex.org/W2128877075","https://openalex.org/W2136189984","https://openalex.org/W2138790992","https://openalex.org/W2143331230","https://openalex.org/W2162059449","https://openalex.org/W2295598076","https://openalex.org/W2396382682","https://openalex.org/W2460087158","https://openalex.org/W2470088391","https://openalex.org/W2507268997","https://openalex.org/W2566147423","https://openalex.org/W2740751575","https://openalex.org/W2741578623","https://openalex.org/W2798598599","https://openalex.org/W2798663050","https://openalex.org/W2809089185","https://openalex.org/W2886518140","https://openalex.org/W2899500964","https://openalex.org/W2940927814","https://openalex.org/W3001344098","https://openalex.org/W3001879867","https://openalex.org/W3021244424","https://openalex.org/W3021300761","https://openalex.org/W3021397474","https://openalex.org/W3035590471","https://openalex.org/W3045745713","https://openalex.org/W3083259433","https://openalex.org/W3099550034","https://openalex.org/W3100107515","https://openalex.org/W3100547398","https://openalex.org/W3102286003","https://openalex.org/W3104914963","https://openalex.org/W3105817677","https://openalex.org/W3133594109","https://openalex.org/W3156166379","https://openalex.org/W3166514800","https://openalex.org/W3175818103","https://openalex.org/W3209981429","https://openalex.org/W3217485291","https://openalex.org/W4205951122","https://openalex.org/W4226315650","https://openalex.org/W4252076394","https://openalex.org/W4289703478","https://openalex.org/W4385245566","https://openalex.org/W6643393412","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W3160516639","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W2387658907","https://openalex.org/W2922169395"],"abstract_inverted_index":{"Neural":[0],"approaches":[1,208],"that":[2,45,99,205],"use":[3],"pre-trained":[4,182],"language":[5],"models":[6,173,212,219,225],"are":[7],"effective":[8],"at":[9],"various":[10],"ranking":[11,166],"tasks,":[12],"such":[13,101],"as":[14,226],"question":[15],"answering":[16],"and":[17,56,108,145,164,196],"ad-hoc":[18],"document":[19,57],"ranking.":[20],"However,":[21,217],"their":[22],"effectiveness":[23],"compared":[24],"to":[25],"feature-based":[26,176],"Learning-to-Rank":[27],"(LtR)":[28],"methods":[29],"has":[30],"not":[31,51,85],"yet":[32],"been":[33],"well-established.":[34],"A":[35],"major":[36],"reason":[37],"for":[38,60,71,153],"this":[39,91],"is":[40],"because":[41],"present":[42,94],"LtR":[43,172,211,218],"benchmarks":[44,68],"contain":[46,52],"query-document":[47,87,110,133],"feature":[48,88,111],"vectors":[49,112],"do":[50,84],"the":[53,64,67,169,175,190,221],"raw":[54],"query":[55],"text":[58,82,107],"needed":[59],"neural":[61,73,184,206,224],"models.":[62],"On":[63],"other":[65],"hand,":[66],"often":[69],"used":[70,113,152],"evaluating":[72],"models,":[74],"e.g.,":[75],"MS":[76],"MARCO,":[77],"TREC":[78],"Robust,":[79],"etc.,":[80],"provide":[81,86],"but":[83],"vectors.":[89],"In":[90],"paper,":[92],"we":[93,203],"Istella22,":[95,202],"a":[96,123,130,142,146,158],"new":[97],"dataset":[98,120],"enables":[100,157],"comparisons":[102],"by":[103,114],"providing":[104],"both":[105],"query/document":[106],"strong":[109,227],"an":[115],"industrial":[116],"search":[117],"engine.":[118],"The":[119],"consists":[121],"of":[122,126,132,148,161,178,194,215],"comprehensive":[124],"corpus":[125],"8.4M":[127],"web":[128],"documents,":[129],"collection":[131],"pairs":[134],"including":[135],"220":[136],"hand-crafted":[137],"features,":[138],"relevance":[139],"judgments":[140],"on":[141,168,189,201],"5-graded":[143],"scale,":[144],"set":[147],"2,198":[149],"textual":[150,192],"queries":[151,195],"testing":[154],"purposes.":[155],"Istella22":[156],"fair":[159],"evaluation":[160],"traditional":[162],"learning-to-rank":[163],"transfer":[165],"techniques":[167],"same":[170],"data.":[171],"exploit":[174],"representations":[177],"training":[179],"samples":[180],"while":[181],"transformer-based":[183],"rankers":[185],"can":[186],"be":[187],"evaluated":[188],"corresponding":[191],"content":[193],"documents.":[197],"Through":[198],"preliminary":[199],"experiments":[200],"find":[204],"re-ranking":[207],"lag":[209],"behind":[210],"in":[213],"terms":[214],"effectiveness.":[216],"identify":[220],"scores":[222],"from":[223],"signals.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-08T00:00:00"}