{"id":"https://openalex.org/W7118622984","doi":"https://doi.org/10.5281/zenodo.18170553","title":"DOREMI Denoised Distantly Supervised Datasets","display_name":"DOREMI Denoised Distantly Supervised Datasets","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118622984","doi":"https://doi.org/10.5281/zenodo.18170553"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18170553","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18170553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18170553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103043214","display_name":"Laura Menotti","orcid":"https://orcid.org/0000-0002-0676-682X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Menotti, Laura","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0002-0676-682X","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003820981","display_name":"Stefano Marchesin","orcid":"https://orcid.org/0000-0003-0362-5893"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"MARCHESIN, STEFANO","raw_affiliation_strings":["University of Padova"],"raw_orcid":"https://orcid.org/0000-0003-0362-5893","affiliations":[{"raw_affiliation_string":"University of Padova","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078254809","display_name":"Gianmaria Silvello","orcid":"https://orcid.org/0000-0003-4970-4554"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvello, Gianmaria","raw_affiliation_strings":["University of Padua"],"raw_orcid":"https://orcid.org/0000-0003-4970-4554","affiliations":[{"raw_affiliation_string":"University of Padua","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6363999843597412},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6333000063896179},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6121000051498413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.3727000057697296},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3589000105857849},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684000134468079},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6121000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5634999871253967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18170553","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18170553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18170553","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18170553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6207606345","display_name":"HetERogeneous sEmantic Data integratIon for the guT-bRain interplaY","funder_award_id":"101137074","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,267],"repository":[1,186],"contains":[2,187],"the":[3,9,16,27,42,48,70,103,117,122,161,169,188,273,277,282,293,308,325,341,356,373],"distant":[4,119,163,176],"denoised":[5,158],"dataset":[6,49,120,177,199,213,236,259],"produced":[7],"using":[8],"DOREMI":[10,38,123,143,195,209,224,247,301,349],"framework.":[11],"DOcument-level":[12],"Relation":[13],"Extraction":[14],"optiMizing":[15],"long":[17],"taIl":[18],"(DOREMI)":[19],"is":[20],"an":[21,66,136],"active":[22],"learning-based":[23],"system":[24],"that":[25,79],"enhances":[26],"training":[28,307,324,355,372],"data":[29],"through":[30],"targeted":[31],"manual":[32],"annotation":[33],"of":[34,72,106,160,179,201,215,238,261,281,292,340],"highly":[35],"informative":[36],"examples.":[37,204,218,241,264],"operates":[39],"upstream":[40],"in":[41,50,69,91,276],"general":[43],"DocRE":[44,57,87,309,326,357,374],"pipeline":[45],"by":[46,111,115,121,135,140,194,208,222,245],"augmenting":[47],"a":[51,73,157],"model-agnostic":[52],"fashion,":[53],"enabling":[54],"any":[55,85],"downstream":[56],"model":[58],"to":[59,83,271],"benefit":[60],"from":[61],"improved":[62],"long-tail":[63,92,144,227,250],"coverage.":[64],"Such":[65],"approach":[67,138],"results":[68,274],"production":[71],"Denoised":[74],"Distantly":[75],"Supervised":[76],"Dataset":[77],"(DDS)":[78],"can":[80],"be":[81],"used":[82,101],"train":[84],"existing":[86],"model,":[88],"demonstrating":[89],"improvements":[90],"relation":[93],"predictions.":[94],"We":[95],"release":[96],"four":[97],"DDSs,":[98],"which":[99],"were":[100,113,133,305,322,353,370],"for":[102,149,232,255,298,315,346,363],"experimental":[104],"evalutation":[105],"DOREMI.":[107],"Two":[108],"datasets":[109,132,155],"(denoted":[110,139],"\"DOREMI\")":[112],"generated":[114,134,193,207,221,244],"cleaning":[116],"DocRED":[118,126,162,175],"framework":[124],"utlizing":[125],"and":[127,172,182,289,332,337],"Re-DocRED.":[128,211],"The":[129,174,185,198,212,235,258,296,313,344,361],"other":[130],"two":[131],"hybrid":[137],"\"DU\"),":[141],"combining":[142,223,246],"predictions":[145,228,251],"with":[146,229,252,311,328,359,376],"UGDRE":[147,230,253],"annotations":[148,231,254],"frequent":[150,233,256],"relations.":[151,234,257],"File":[152],"Outline":[153],"All":[154],"are":[156],"version":[159],"dataset.":[164],"Hence,":[165],"they":[166],"all":[167],"contain":[168],"same":[170],"documents":[171,181],"entities.":[173,184],"consists":[178,200,214,237,260],"101,873":[180],"1,965,484":[183],"following":[189],"files:":[190],"DOREMI-DDS-DocRED.json:":[191],"DDS":[192,206,220,243],"utilizing":[196,210,300,317,348,365],"DocRED.":[197],"1,704,161":[202],"positive":[203,217,240,263],"DOREMI-DDS-ReDocRED.json:":[205],"3,957,238":[216],"DU-DDS-DocRED.json:":[219],"(utilizing":[225,248],"DocRED)":[226],"1,726,707":[239],"DU-DDS-ReDocRED.json:":[242],"Re-DocRED)":[249],"1,796,229":[262],"Reproducibility":[265],"Guidelines":[266],"section":[268,280],"describes":[269],"how":[270],"obtain":[272],"presented":[275],"\"Experimental":[278],"Results\"":[279],"paper.":[283],"Table":[284],"4":[285],"(and":[286,334],"Tables":[287,330,335],"A8":[288,336],"B10":[290,338],"(a)":[291],"Technical":[294,342],"Appendix)":[295],"performances":[297,314,345,362],"rows":[299,316,347,364],"as":[302,319,350,367],"Distant":[303,320,351,368],"Data":[304,321,352,369],"obtained":[306,323,354,371],"models":[310,327,358,375],"DOREMI-DDS-DocRED.json.":[312],"D+U":[318,366],"DU-DDS-DocRED.json.":[329],"5":[331],"6":[333],"(b)":[339],"Appendix))":[343],"DOREMI-DDS-ReDocRED.json.":[360],"DU-DDS-ReDocRED.json.":[377]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-01-08T00:00:00"}