{"id":"https://openalex.org/W7166826684","doi":"https://doi.org/10.18653/v1/2026.acl-srw.44","title":"Does Locality Cost in Polish Medical Text Classification? Duplicate-Aware Evaluation of Federated Learning","display_name":"Does Locality Cost in Polish Medical Text Classification? Duplicate-Aware Evaluation of Federated Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166826684","doi":"https://doi.org/10.18653/v1/2026.acl-srw.44"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-srw.44","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-srw.44","pdf_url":"https://aclanthology.org/2026.acl-srw.44.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-srw.44.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139818716","display_name":"Daniel Cie\u015blak","orcid":null},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Daniel Cie\u015blak","raw_affiliation_strings":["Gda\u0144sk University of Technology Multimedia Systems Department Gda\u0144sk University of Technology Multimedia Systems Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gda\u0144sk University of Technology Multimedia Systems Department Gda\u0144sk University of Technology Multimedia Systems Department","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139795240","display_name":"Andrzej Czy\u017cewski","orcid":null},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej Czy\u017cewski","raw_affiliation_strings":["Gda\u0144sk University of Technology Multimedia Systems Department Gda\u0144sk University of Technology Multimedia Systems Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gda\u0144sk University of Technology Multimedia Systems Department Gda\u0144sk University of Technology Multimedia Systems Department","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169333911"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81631025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"498","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.34369999170303345,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.34369999170303345,"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/T11719","display_name":"Data Quality and Management","score":0.09860000014305115,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.061500001698732376,"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/locality","display_name":"Locality","score":0.49619999527931213},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.415800005197525},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3138999938964844},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.26109999418258667},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.26030001044273376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668999791145325},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-srw.44","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-srw.44","pdf_url":"https://aclanthology.org/2026.acl-srw.44.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-srw.44","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-srw.44","pdf_url":"https://aclanthology.org/2026.acl-srw.44.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44423535466194153,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166826684.pdf","grobid_xml":"https://content.openalex.org/works/W7166826684.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,123],"is":[2,36,114,124],"often":[3],"framed":[4],"as":[5],"a":[6,26,73],"practical":[7],"trade-off":[8],"in":[9,25,57,140],"clinical":[10],"NLP:":[11],"safer":[12],"data":[13],"handling":[14],"at":[15],"the":[16,39,81,91],"cost":[17],"of":[18,29,97,105],"lower":[19],"predictive":[20],"performance.We":[21],"revisit":[22],"this":[23,141],"assumption":[24],"benchmark-specific":[27],"study":[28],"Polish":[30,143],"medical":[31,144],"text":[32,50,145],"classification.A":[33],"key":[34],"issue":[35],"evaluation":[37,153],"granularity:":[38],"test":[40],"split":[41],"contains":[42],"10,634":[43],"rows":[44],"but":[45],"only":[46],"670":[47],"unique":[48],"normalized":[49],"hashes,":[51],"with":[52],"18":[53],"inconsistent":[54],"groups":[55],"removed":[56],"strict":[58],"grouped":[59],"evaluation.We":[60],"therefore":[61],"compare":[62],"centralized":[63,92,128],"and":[64,72,102],"federated":[65,85,122],"training":[66,86],"under":[67],"both":[68],"conventional":[69],"instance-level":[70,95],"scoring":[71],"stricter":[74],"hash-level":[75,103],"protocol":[76],"that":[77,121,139],"controls":[78],"duplicate":[79],"inflation.In":[80],"strongest":[82],"reported":[83],"settings,":[84],"matches":[87],"or":[88],"slightly":[89],"exceeds":[90],"baseline,":[93],"reaching":[94],"Macro-F1":[96,104],"0.8826\u00b10.0177versus":[98],"0.8689":[99],"\u00b1":[100,107,111],"0.0124,":[101],"0.8908":[106],"0.0220":[108],"versus":[109],"0.8841":[110],"0.0078.The":[112],"claim":[113,133],"deliberately":[115],"narrow:":[116],"we":[117,132,137],"do":[118,131],"not":[119],"argue":[120],"generally":[125],"superior":[126],"to":[127],"training,":[129],"nor":[130],"formal":[134],"privacy":[135],"guarantees.Rather,":[136],"show":[138],"duplicate-heavy":[142],"benchmark,":[146],"conclusions":[147],"about":[148],"locality":[149],"depend":[150],"strongly":[151],"on":[152],"hygiene.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}