{"id":"https://openalex.org/W4414578095","doi":"https://doi.org/10.1007/s10579-025-09881-w","title":"JurisTCU: a Brazilian Portuguese information retrieval dataset with query relevance judgments","display_name":"JurisTCU: a Brazilian Portuguese information retrieval dataset with query relevance judgments","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W4414578095","doi":"https://doi.org/10.1007/s10579-025-09881-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-025-09881-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09881-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09881-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09881-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084870570","display_name":"Leandro Car\u00edsio Fernandes","orcid":"https://orcid.org/0000-0002-4114-2334"},"institutions":[{"id":"https://openalex.org/I4210149835","display_name":"Instituto do Cora\u00e7\u00e3o","ror":"https://ror.org/04x2nj883","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210149835"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Leandro Car\u00edsio Fernandes","raw_affiliation_strings":["C\u00e2mara dos Deputados, Bras\u00edlia, Brazil","Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-4114-2334","affiliations":[{"raw_affiliation_string":"C\u00e2mara dos Deputados, Bras\u00edlia, Brazil","institution_ids":[]},{"raw_affiliation_string":"Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I4210149835"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leandro dos Santos Ribeiro","orcid":"https://orcid.org/0009-0008-3715-9927"},"institutions":[{"id":"https://openalex.org/I4210149835","display_name":"Instituto do Cora\u00e7\u00e3o","ror":"https://ror.org/04x2nj883","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210149835"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Leandro dos Santos Ribeiro","raw_affiliation_strings":["Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0009-0008-3715-9927","affiliations":[{"raw_affiliation_string":"Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I4210149835"]},{"raw_affiliation_string":"Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marcos Vin\u00edcius Borela de Castro","orcid":"https://orcid.org/0009-0000-8633-1385"},"institutions":[{"id":"https://openalex.org/I4210149835","display_name":"Instituto do Cora\u00e7\u00e3o","ror":"https://ror.org/04x2nj883","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210149835"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Marcos Vin\u00edcius Borela de Castro","raw_affiliation_strings":["Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0009-0000-8633-1385","affiliations":[{"raw_affiliation_string":"Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I4210149835"]},{"raw_affiliation_string":"Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Leonardo Augusto da Silva Pacheco","orcid":"https://orcid.org/0000-0001-6506-2366"},"institutions":[{"id":"https://openalex.org/I4210149835","display_name":"Instituto do Cora\u00e7\u00e3o","ror":"https://ror.org/04x2nj883","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210149835"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Leonardo Augusto da Silva Pacheco","raw_affiliation_strings":["Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-6506-2366","affiliations":[{"raw_affiliation_string":"Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I4210149835"]},{"raw_affiliation_string":"Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058639233","display_name":"Edans F. O. Sandes","orcid":"https://orcid.org/0000-0001-9502-7799"},"institutions":[{"id":"https://openalex.org/I4210149835","display_name":"Instituto do Cora\u00e7\u00e3o","ror":"https://ror.org/04x2nj883","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210149835"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Edans Fl\u00e1vius de Oliveira Sandes","raw_affiliation_strings":["Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil"],"raw_orcid":"https://orcid.org/0009-0004-4553-4783","affiliations":[{"raw_affiliation_string":"Instituto Serzedello Corr\u00eaa (ISC), Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I4210149835"]},{"raw_affiliation_string":"Tribunal de Contas da Uni\u00e3o (TCU), Bras\u00edlia, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058639233","https://openalex.org/A5084870570"],"corresponding_institution_ids":["https://openalex.org/I4210149835"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0083632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"60","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"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":0.9957000017166138,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9739999771118164,"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":0.9718000292778015,"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/relevance","display_name":"Relevance (law)","score":0.8149999976158142},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.569100022315979},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.40860000252723694},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3635999858379364},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.3521000146865845},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.31470000743865967},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8149999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6791999936103821},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.3521000146865845},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C182861755","wikidata":"https://www.wikidata.org/wiki/Q5158391","display_name":"Concept search","level":4,"score":0.25589999556541443},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10579-025-09881-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09881-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09881-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2503.08379","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08379","pdf_url":"https://arxiv.org/pdf/2503.08379","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2503.08379","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.08379","pdf_url":"https://arxiv.org/pdf/2503.08379","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08379","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08379","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s10579-025-09881-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09881-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09881-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414578095.pdf","grobid_xml":"https://content.openalex.org/works/W4414578095.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W4403577276","https://openalex.org/W2951534261","https://openalex.org/W4313445468","https://openalex.org/W4287018294","https://openalex.org/W4394736771","https://openalex.org/W4414839374","https://openalex.org/W4286911907","https://openalex.org/W4405767463","https://openalex.org/W4392619035","https://openalex.org/W4405884222","https://openalex.org/W2057495142","https://openalex.org/W4404356582","https://openalex.org/W4387221840","https://openalex.org/W4287079430","https://openalex.org/W4389747551","https://openalex.org/W3137305332","https://openalex.org/W4400064731","https://openalex.org/W4379251652","https://openalex.org/W3099700870","https://openalex.org/W6929517872","https://openalex.org/W3092952717","https://openalex.org/W4213009331","https://openalex.org/W4389747470","https://openalex.org/W4389519438","https://openalex.org/W2937036051","https://openalex.org/W4284691825","https://openalex.org/W4403006857","https://openalex.org/W2970641574","https://openalex.org/W3096266342","https://openalex.org/W4404402271","https://openalex.org/W4386908049","https://openalex.org/W2593088329","https://openalex.org/W4401673053","https://openalex.org/W4391840390","https://openalex.org/W3154180753"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"introduces":[3],"JurisTCU":[4,91],",":[5],"a":[6,79,186,205],"Brazilian":[7,31,211],"Portuguese":[8],"dataset":[9,16,187],"for":[10,163,188,195],"legal":[11],"information":[12],"retrieval":[13],"(LIR).":[14],"The":[15,56],"is":[17],"freely":[18],"available":[19],"(":[20],"https://huggingface.co/datasets/LeandroRibeiro/JurisTCU":[21],")":[22],"and":[23,70,101,105,133,160],"consists":[24],"of":[25,34,48,119,154],"16,045":[26],"jurisprudential":[27],"documents":[28],"from":[29],"the":[30,46,111,117,142,145,149,179,189,199],"Federal":[32],"Court":[33],"Accounts,":[35],"along":[36],"with":[37,41,52,85,126,152],"150":[38],"queries":[39,57],"annotated":[40],"relevance":[42,54],"judgments.":[43],"It":[44],"addresses":[45],"scarcity":[47],"Portuguese-language":[49,190],"LIR":[50],"datasets":[51],"query":[53],"annotations.":[55],"are":[58],"organized":[59],"into":[60],"three":[61],"groups:":[62],"real":[63],"user":[64],"keyword-based":[65,68,139,165],"queries,":[66,69,166],"synthetic":[67,71],"question-based":[72],"queries.":[73,140],"Relevance":[74],"judgments":[75],"were":[76],"produced":[77,148],"through":[78],"hybrid":[80],"approach":[81],"combining":[82],"LLM-based":[83],"scoring":[84],"expert":[86],"domain":[87],"validation.":[88],"We":[89,108],"used":[90],"in":[92,130,157,175],"14":[93],"experiments":[94],"using":[95],"lexical":[96,182],"search":[97,103,122,197,206],"(document":[98],"expansion":[99,113],"methods)":[100],"semantic":[102,173],"(BERT-based":[104],"OpenAI":[106,146],"embeddings).":[107],"show":[109],"that":[110,168],"document":[112],"methods":[114],"significantly":[115],"improve":[116],"performance":[118],"standard":[120],"BM25":[121],"on":[123,181],"this":[124,176],"dataset,":[125],"improvements":[127,153],"exceeding":[128],"45%":[129],"P@10,":[131,158],"R@10,":[132,159],"nDCG@10":[134,161],"metrics":[135,162],"when":[136],"evaluating":[137,196],"short":[138,164],"Among":[141],"embedding":[143],"models,":[144],"models":[147],"best":[150],"results,":[151],"approximately":[155],"70%":[156],"suggesting":[167],"these":[169],"dense":[170],"embeddings":[171],"capture":[172],"relationships":[174],"domain,":[177],"surpassing":[178],"reliance":[180],"terms.":[183],"Besides":[184],"offering":[185],"IR":[191],"research":[192],"community,":[193],"suitable":[194],"systems,":[198],"results":[200],"also":[201],"contribute":[202],"to":[203,210],"enhancing":[204],"system":[207],"highly":[208],"relevant":[209],"citizens.":[212]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-09-28T00:00:00"}
