{"id":"https://openalex.org/W4401042758","doi":"https://doi.org/10.18653/v1/2024.vardial-1.15","title":"Studying Language Variation Considering the Re-Usability of Modern Theories, Tools and Resources for Annotating Explicit and Implicit Events in Centuries Old Text","display_name":"Studying Language Variation Considering the Re-Usability of Modern Theories, Tools and Resources for Annotating Explicit and Implicit Events in Centuries Old Text","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042758","doi":"https://doi.org/10.18653/v1/2024.vardial-1.15"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.15","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.15","pdf_url":"https://aclanthology.org/2024.vardial-1.15.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.vardial-1.15.pdf","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"},"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":true,"raw_author_name":"Stella Verkijk","raw_affiliation_strings":["Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012219972","display_name":"Pia Sommerauer","orcid":"https://orcid.org/0000-0003-3593-1465"},"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":"Pia Sommerauer","raw_affiliation_strings":["Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003791447","display_name":"Piek Vossen","orcid":"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":"Piek Vossen","raw_affiliation_strings":["Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam Huygens Institute Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025435123"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09593789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/usability","display_name":"Usability","score":0.7980103492736816},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7899574041366577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746752500534058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43478235602378845},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36623507738113403},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3347417116165161},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.24650320410728455},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08864197134971619}],"concepts":[{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.7980103492736816},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7899574041366577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746752500534058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43478235602378845},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36623507738113403},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3347417116165161},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24650320410728455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08864197134971619},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.15","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.15","pdf_url":"https://aclanthology.org/2024.vardial-1.15.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:publications/fa7124bf-a9b0-4513-8ab1-30c36038a9d1","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/fa7124bf-a9b0-4513-8ab1-30c36038a9d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Verkijk, S, Sommerauer, P & Vossen, P T J M 2024, Studying Language Variation Considering the Re-Usability of Modern Theories, Tools and Resources for Annotating Explicit and Implicit Events in Centuries Old Text. in Y Scherrer, T Jauhiainen, N Ljubesic, M Zampieri, P Nakov & J Tiedemann (eds), Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024). Association for Computational Linguistics (ACL), pp. 174-187, 11th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial 2024, Mexico City, Mexico, 20/06/24. https://doi.org/10.18653/v1/2024.vardial-1.15","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/fa7124bf-a9b0-4513-8ab1-30c36038a9d1","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/fa7124bf-a9b0-4513-8ab1-30c36038a9d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Verkijk, S, Sommerauer, P & Vossen, P T J M 2024, Studying Language Variation Considering the Re-Usability of Modern Theories, Tools and Resources for Annotating Explicit and Implicit Events in Centuries Old Text. in Y Scherrer, T Jauhiainen, N Ljubesic, M Zampieri, P Nakov & J Tiedemann (eds), Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024). Association for Computational Linguistics (ACL), pp. 174-187, 11th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial 2024, Mexico City, Mexico, 20/06/24. https://doi.org/10.18653/v1/2024.vardial-1.15","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.vardial-1.15","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.15","pdf_url":"https://aclanthology.org/2024.vardial-1.15.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1702942281","display_name":"General Letters Ontology Based AccessibiLity InfraStructure (GLOBALISE)","funder_award_id":"175.2019.003","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042758.pdf","grobid_xml":"https://content.openalex.org/works/W4401042758.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W4389670110","https://openalex.org/W2356521405","https://openalex.org/W2429057255","https://openalex.org/W2187546663","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W4315621326","https://openalex.org/W2899790217","https://openalex.org/W2598865957"],"abstract_inverted_index":{"This":[0],"paper":[1,63],"discusses":[2],"the":[3,13,32,54,121,139,475,481,487,821,827,833],"re-usability":[4],"of":[5,19,25,31,46,49],"existing":[6],"approaches,":[7],"tools":[8,98],"and":[9,16,41,53,73,88,97,130,144],"automatic":[10,17,56],"techniques":[11],"for":[12,76,84,100],"manual":[14],"annotation":[15,39,82,140],"extraction":[18],"events":[20],"in":[21,29,127,284],"a":[22,43,491,837],"challenging":[23],"variant":[24],"centuries":[26],"old":[27],"Dutch":[28,33,87,102],"documents":[30],"East":[34],"India":[35],"Company.We":[36],"describe":[37],"our":[38],"process":[40],"provide":[42],"thorough":[44],"analysis":[45],"different":[47],"versions":[48],"manually":[50],"annotated":[51,142],"data":[52],"first":[55],"results":[57],"from":[58],"two":[59],"fine-tuned":[60],"Language":[61],"Models.The":[62],"studies":[64],"to":[65,79,89,118,341,480,688,826],"what":[66,90],"extent":[67,91],"we":[68,92],"can":[69,93],"use":[70,94],"NLP":[71,95],"theories":[72],"tasks":[74],"formulated":[75],"modern":[77,86,101,108],"English":[78],"design":[80],"an":[81],"task":[83],"early":[85,107],"models":[96],"built":[99],"(and":[103],"other":[104],"languages)":[105],"on":[106],"Dutch.We":[109],"believe":[110],"these":[111],"analyses":[112],"give":[113],"us":[114],"insight":[115],"into":[116],"how":[117,131],"deal":[119],"with":[120,470,816],"large":[122],"variation":[123,133],"that":[124],"language":[125],"shows":[126],"describing":[128],"events,":[129],"this":[132],"may":[134],"differ":[135],"across":[136],"domains.We":[137],"release":[138],"guidelines,":[141],"data,":[143],"code":[145],"(https://github.":[146],"com/StellaVerkijk/VarDial2024).RobBERT":[147],"XLM-R":[148],"Masked":[149,496],"token":[150,477,489,497,823,835],"Prediction":[151,155,498,502],"Probability":[152,156,499,503],"L2C?":[153,157,500,504],"FW?":[154,158,501,505],"ontfangst":[159,506],"grond":[160,164,198,525,537],"0.26":[161],"no":[162,163,166,167,171,172,175,176,180,184,185,188,189,192,193,196,200,201,205,206,209,210,214,215,218,219,223,224,227,228,231,235,236,239,240,243,244,248,249,252,257,261,266,270,274,275,278,279,282,283,286,291,295,300,304,305,309,313,314,317,318,321,322,325,326,329,334,335,338,339,345,346,349,350,354,355,358,362,366,370,371,374,379,383,388,392,397,401,405,409,413,414,417,418,422,423,426,431,432,435,440,441,444,445,448,452,453,456,460,461,509,510,514,518,519,522,523,527,528,531,532,535,536,539,540,543,547,548,552,553,557,561,562,565,566,570,571,574,575,578,579,582,583,586,587,591,595,600,604,609,613,617,618,621,622,626,629,630,633,638,642,643,647,648,651,656,657,660,661,665,668,669,672,676,677,681,682,685,686,692,693,696,697,701,705,706,709,713,714,717,721,722,726,730,735,736,739,740,744,748,749,752,757,760,764,765,769,770,774,778,782,783,787,788,791,792,795,796,800,803,804,807],"0.55":[165],"(reception)":[168,515],"basis":[169,173],"0.13":[170,637,772],"0.01":[174,183,191,199,281,361,369,455,459,624,671],"Getting":[177,524],"een":[178,268],"0.09":[179,387,695,704,725],"yes":[181,197,232,253,258,262,267,271,287,292,296,301,310,330,359,363,367,375,380,384,389,393,398,402,406,410,427,436,449,457,513,544,556,590,596,599,605,608,614,625,634,639,652,664,673,702,710,718,727,731,745,753,756,761,773,779,799],"Grund":[182],"straffe":[186],"0.05":[187,213,247,299,357,603,700,712,720,729,734,738],"aanleiding":[190],"elk":[194],"0.02":[195,226,234,242,265,273,285,303,312,316,320,324,328,344,353,365,373,412,439,447,451,628,646,655,659,663,667,675,751,759,777,786,794,802],"versoucken":[202,549],"weten":[203,207,550,572],"0.15":[204,569],"0.77":[208],"(requesting)":[211,558],"zien":[212,216],"0.04":[217,222,230,269,294,308,391,400,408,526,534,546,573,577,641,743,747,755,806],"Request":[220,567],"staan":[221],"wissen":[225],"toe":[229,649],"merken":[233],"zeggen":[237],"0.03":[238,256,277,416,430,434,443,542,581,585,589,612,620,650,708,716,763],"horen":[241],"ordre":[245,507,592,597],"is":[246,276,352,420,478,490,767,824,836],"de":[250,395],"0.21":[251],"(order/instruction)":[254,601],"om":[255,715],",":[259,264,298,327,356,377,381,424,593,670,724,728,776],"0.07":[260,333,348,594,607,768,798],"SocialInteraction":[263,610],"heeft":[272],"bekent":[280],"geeven":[288,635,662],"te":[289,293,636],"0.10":[290,517,521],"(giving)":[297,644],"reeds":[302],"Giving":[306,653],"niet":[307],"al":[311],"kan":[315,658],"betalen":[319],"sal":[323,654,674],"verpligt":[331,678],"meer":[332,336,690,694],"0.12":[337,421],"(obliged/":[340,687],"oblige)":[342,689],"anders":[343,679,683],"langer":[347,703],"ForceToAct":[351,698],"ook":[360],"zoo":[364],"zijnde":[368],"zo":[372],"belastinge":[376,723],"0.39":[378],"0.30":[382],"(tax)":[385,732],"en":[386,407],"d":[390],"FinancialTransaction":[394,437,741,784],"0.08":[396,425,530,781,790],"s":[399],"ende":[403,541,750],"0.06":[404,538,564,616],"daer":[411,627],"der":[415],"aengereekend":[419,766],"(charged)":[428,775],"wordt":[429],"aan":[433],"eert":[438],"zal":[442],"e":[446],"naar":[450],"int":[454],"dient":[458],"Table":[462],"11:":[463],"Top":[464,810],"5":[465,811],"predicted":[466,476,488,812,822,834],"tokens":[467,813],"per":[468,814],"model":[469,815],"probability":[471,817],"scores.L2C":[472,818],"=":[473,485,819,831],"whether":[474,486,820,832],"linkable":[479,825],"corresponding":[482,828],"event":[483,829],"class.FW":[484,830],"function":[492,838],"word.186":[493],"GysBERT":[494],"GysBERT-v2":[495],"0.17":[508,680],"ontfang":[511],"0.14":[512,691],"copie":[516],"antwoorde":[520],"antwoord":[529],"last":[533],"dato":[545],"0.27":[551],"versoeken":[554],"0.70":[555],"weeten":[559,580],"0.24":[560],"dienen":[563],"volgen":[568],"blijken":[576],"verstaan":[584],"versoecken":[588],"0.82":[598],"soo":[602],"ordres":[606],"dat":[611],"vast":[615,619],"order":[623],"uijt":[631],"0.00":[632],"soude":[640],"doen":[645],"moet":[666],"0.41":[684],"deselve":[699,719],"die":[707,742],"verder":[711],"cours":[733],"verwagting":[737],"verantwoording":[746],"factuur":[754],"##waerts":[758],"gebruijk":[762],"belast":[771],"gebragt":[780],"gebracht":[785],"overgebragt":[789],"overgegeven":[793],"verantwoord":[797],"gehouden":[801],"toegesonden":[805],"noTable":[808],"12:":[809],"word.":[839]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}