{"id":"https://openalex.org/W7204226345","doi":"https://doi.org/10.48550/arxiv.2608.24268","title":"ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts","display_name":"ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204226345","doi":"https://doi.org/10.48550/arxiv.2608.24268"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24268","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24268","pdf_url":"https://arxiv.org/pdf/2608.24268","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025435123","display_name":"Stella Verkijk","orcid":"https://orcid.org/0009-0000-9263-2272","observed_orcids":["https://orcid.org/0009-0000-9263-2272"]},"institutions":[{"id":"https://openalex.org/I2801908541","display_name":"Huygens Institute for History and Culture of the Netherlands","ror":"https://ror.org/04x6kq749","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I2801908541"]},{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Verkijk, Stella","raw_affiliation_strings":["Huygens Instituut","Vrije Universiteit Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huygens Instituut","institution_ids":["https://openalex.org/I2801908541"]},{"raw_affiliation_string":"Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003791447","display_name":"Piek T. J. M. Vossen","orcid":"https://orcid.org/0000-0002-6238-5941","observed_orcids":["https://orcid.org/0000-0002-6238-5941"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vossen, Piek","raw_affiliation_strings":["Vrije Universiteit Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9531000256538391,"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":0.9531000256538391,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0066999997943639755,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.004999999888241291,"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/historical-texts","display_name":"historical texts","score":0.4180000126361847},{"id":"https://openalex.org/keywords/17th-and-18th-centuries","display_name":"17th-18th century","score":0.7960000038146973},{"id":"https://openalex.org/keywords/frequency-bias","display_name":"frequency bias","score":0.621999979019165},{"id":"https://openalex.org/keywords/underrepresented-classes","display_name":"underrepresented classes","score":0.628000020980835},{"id":"https://openalex.org/keywords/classifier-combination","display_name":"classifier combination","score":0.718999981880188},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.781000018119812},{"id":"https://openalex.org/keywords/domain-specific-data-augmentation","display_name":"domain-specific data augmentation","score":0.6029999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522000193595886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43560001254081726},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24268","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24268","pdf_url":"https://arxiv.org/pdf/2608.24268","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,"listed_in":[],"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.2608.24268","doi":"https://doi.org/10.48550/arxiv.2608.24268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24268","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24268","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24268","pdf_url":"https://arxiv.org/pdf/2608.24268","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,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204226345.pdf","grobid_xml":"https://content.openalex.org/works/W7204226345.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7131782360","https://openalex.org/W4386566782","https://openalex.org/W4284707204","https://openalex.org/W2742263117","https://openalex.org/W2127194753","https://openalex.org/W4367308305","https://openalex.org/W4288260269","https://openalex.org/W2347004576","https://openalex.org/W7140113711","https://openalex.org/W4412888068"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"methods":[3,23],"to":[4,27,67,123,132,141,154],"extract":[5,68],"over":[6],"50":[7],"types":[8],"of":[9,39,60,88,136,162,195],"events":[10,69,90,116],"from":[11,44],"a":[12,29,52,151,165,171,177,187,193],"Dutch":[13],"historical":[14],"corpus":[15],"spanning":[16],"the":[17,37,40,46,58,74,89,93,105,143],"17th":[18],"and":[19,64,176],"18th":[20],"centuries.":[21],"The":[22,183],"we":[24,65],"propose":[25,82,150],"aim":[26,66],"tackle":[28],"very":[30],"challenging":[31],"scenario":[32],"in":[33,50,57,73,92,104,174,180,190,198],"Machine":[34],"Learning:":[35],"extracting":[36],"long-tail":[38,196],"long-tail.":[41],"Historic":[42],"data":[43,76,107,201],"before":[45],"19th":[47],"century":[48],"is":[49],"itself":[51],"niche":[53,200],"domain":[54],"not":[55],"covered":[56],"pre-training":[59],"Large":[61],"Language":[62],"Models,":[63],"only":[70],"scarcely":[71],"annotated":[72],"training":[75,94,106],"available":[77],"for":[78,86,192],"this":[79,133],"domain.":[80],"We":[81,96,130,148],"creating":[83],"expert":[84],"classifiers":[85],"subgroups":[87],"present":[91],"data.":[95,158],"make":[97],"these":[98],"groupings":[99],"based":[100],"on":[101,109,114],"similar":[102],"frequency":[103,128],"or":[108],"semantic":[110],"relatedness.":[111],"Experts":[112],"trained":[113],"underrepresented":[115],"are":[117],"assigned":[118],"higher":[119],"priority":[120],"when":[121],"predicting":[122],"avoid":[124],"being":[125],"dominated":[126],"by":[127],"biases.":[129],"refer":[131],"new":[134],"way":[135],"combining":[137],"classifiers,":[138],"specifically":[139],"tailored":[140],"protect":[142],"long-tail,":[144],"as":[145],"ROBE:":[146],"Reversed-Order-Biased-Experts.":[147],"also":[149],"controlled":[152],"method":[153],"create":[155],"domain-specific":[156],"synthetic":[157],"Our":[159],"two":[160],"implementations":[161],"ROBE":[163],"outperform":[164],"simple":[166],"fine-tuned":[167],"encoder":[168],"model":[169,185],"with":[170],".16":[172],"increase":[173,179,189],"precision":[175],".05":[178],"recall":[181],"respectively.":[182],"best":[184],"achieves":[186],".11":[188],"f1":[191],"group":[194],"classes":[197],"our":[199],"set.":[202]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}