{"id":"https://openalex.org/W4393163454","doi":"https://doi.org/10.1162/coli_a_00516","title":"Analyzing Dataset Annotation Quality Management in the Wild","display_name":"Analyzing Dataset Annotation Quality Management in the Wild","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393163454","doi":"https://doi.org/10.1162/coli_a_00516"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00516","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00516","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00516/2351693/coli_a_00516.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00516/2351693/coli_a_00516.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070380110","display_name":"Jan-Christoph Klie","orcid":"https://orcid.org/0000-0003-0181-6450"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jan-Christoph Klie","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Department of Computer Science and Hessian Center for AI (hessian.AI). www.ukp.tu-darmstadt.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Department of Computer Science and Hessian Center for AI (hessian.AI). www.ukp.tu-darmstadt.de","institution_ids":["https://openalex.org/I16718484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091796714","display_name":"Richard Eckart de Castilho","orcid":"https://orcid.org/0000-0003-0991-7045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Eckart de Castilho","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027450194","https://openalex.org/A5070380110"],"corresponding_institution_ids":["https://openalex.org/I16718484"],"apc_list":null,"apc_paid":null,"fwci":11.501,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98713075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"50","issue":"3","first_page":"817","last_page":"866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9929999709129333,"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/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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/annotation","display_name":"Annotation","score":0.6882094144821167},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5780211687088013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5142862200737},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.370303213596344},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.334369957447052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2219410240650177}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6882094144821167},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5780211687088013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5142862200737},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.370303213596344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.334369957447052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2219410240650177},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00516","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00516","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00516/2351693/coli_a_00516.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9c98640f81324a218857826b18cb375e","is_oa":true,"landing_page_url":"https://doaj.org/article/9c98640f81324a218857826b18cb375e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 50, Iss 3 (2024)","raw_type":"article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:146086","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/146086/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00516","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00516","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00516/2351693/coli_a_00516.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5621129062","display_name":null,"funder_award_id":"GU 798/27-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393163454.pdf"},"referenced_works_count":160,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W82998145","https://openalex.org/W172170795","https://openalex.org/W1543648998","https://openalex.org/W1568955415","https://openalex.org/W1594247117","https://openalex.org/W1829168467","https://openalex.org/W1840435438","https://openalex.org/W1962580118","https://openalex.org/W1970381522","https://openalex.org/W1975879668","https://openalex.org/W1996772855","https://openalex.org/W2007963708","https://openalex.org/W2011067361","https://openalex.org/W2012378416","https://openalex.org/W2013378101","https://openalex.org/W2015795623","https://openalex.org/W2021664962","https://openalex.org/W2053154970","https://openalex.org/W2061504941","https://openalex.org/W2064454539","https://openalex.org/W2069378996","https://openalex.org/W2076898331","https://openalex.org/W2104630935","https://openalex.org/W2105824687","https://openalex.org/W2107598941","https://openalex.org/W2112688502","https://openalex.org/W2127849236","https://openalex.org/W2129494713","https://openalex.org/W2132309340","https://openalex.org/W2133943399","https://openalex.org/W2141403362","https://openalex.org/W2141766660","https://openalex.org/W2144578941","https://openalex.org/W2150290224","https://openalex.org/W2153222072","https://openalex.org/W2153804780","https://openalex.org/W2154950285","https://openalex.org/W2158428778","https://openalex.org/W2158880898","https://openalex.org/W2160375265","https://openalex.org/W2162233306","https://openalex.org/W2164777277","https://openalex.org/W2166247043","https://openalex.org/W2166957049","https://openalex.org/W2170021941","https://openalex.org/W2170493558","https://openalex.org/W2187912528","https://openalex.org/W2201853392","https://openalex.org/W2250309026","https://openalex.org/W2250600206","https://openalex.org/W2250626167","https://openalex.org/W2251659640","https://openalex.org/W2251818274","https://openalex.org/W2251939518","https://openalex.org/W2265312303","https://openalex.org/W2295951612","https://openalex.org/W2318014128","https://openalex.org/W2328893508","https://openalex.org/W2472097883","https://openalex.org/W2477907264","https://openalex.org/W2614908767","https://openalex.org/W2616203426","https://openalex.org/W2625465398","https://openalex.org/W2739351760","https://openalex.org/W2759211898","https://openalex.org/W2763103160","https://openalex.org/W2765320432","https://openalex.org/W2782152208","https://openalex.org/W2787715834","https://openalex.org/W2793692009","https://openalex.org/W2798935874","https://openalex.org/W2889470921","https://openalex.org/W2890894339","https://openalex.org/W2899689163","https://openalex.org/W2911227954","https://openalex.org/W2917820468","https://openalex.org/W2949600515","https://openalex.org/W2951286828","https://openalex.org/W2952087486","https://openalex.org/W2952179106","https://openalex.org/W2962843773","https://openalex.org/W2964120912","https://openalex.org/W2964223283","https://openalex.org/W2970024917","https://openalex.org/W2970352191","https://openalex.org/W2970442950","https://openalex.org/W2971039193","https://openalex.org/W2971299805","https://openalex.org/W2979417040","https://openalex.org/W2990787438","https://openalex.org/W3031359449","https://openalex.org/W3034238904","https://openalex.org/W3034323190","https://openalex.org/W3034891697","https://openalex.org/W3093779786","https://openalex.org/W3098135292","https://openalex.org/W3098323839","https://openalex.org/W3104382126","https://openalex.org/W3113417490","https://openalex.org/W3114242174","https://openalex.org/W3118813946","https://openalex.org/W3135371071","https://openalex.org/W3152936485","https://openalex.org/W3154945374","https://openalex.org/W3156669901","https://openalex.org/W3159682551","https://openalex.org/W3169654142","https://openalex.org/W3171896931","https://openalex.org/W3175287561","https://openalex.org/W3175362313","https://openalex.org/W3176214425","https://openalex.org/W3177629344","https://openalex.org/W3193717459","https://openalex.org/W3199745369","https://openalex.org/W3212368439","https://openalex.org/W4200444669","https://openalex.org/W4205508242","https://openalex.org/W4226278401","https://openalex.org/W4232519079","https://openalex.org/W4234180827","https://openalex.org/W4234306800","https://openalex.org/W4243479147","https://openalex.org/W4243989635","https://openalex.org/W4283155630","https://openalex.org/W4285292976","https://openalex.org/W4286987939","https://openalex.org/W4287252712","https://openalex.org/W4292341621","https://openalex.org/W4294152847","https://openalex.org/W4299905303","https://openalex.org/W4300944962","https://openalex.org/W4303614602","https://openalex.org/W4313908941","https://openalex.org/W4320350303","https://openalex.org/W4328001368","https://openalex.org/W4385572111","https://openalex.org/W4385791713","https://openalex.org/W4386566763","https://openalex.org/W4395677977","https://openalex.org/W6606988585","https://openalex.org/W6652440384","https://openalex.org/W6679098003","https://openalex.org/W6679805048","https://openalex.org/W6682780409","https://openalex.org/W6684468177","https://openalex.org/W6686981222","https://openalex.org/W6687705047","https://openalex.org/W6691459498","https://openalex.org/W6691601049","https://openalex.org/W6691846970","https://openalex.org/W6748010019","https://openalex.org/W6751678649","https://openalex.org/W6753942111","https://openalex.org/W6778689171","https://openalex.org/W6793012311","https://openalex.org/W6800875267","https://openalex.org/W6810738896","https://openalex.org/W6849397646","https://openalex.org/W6865393773"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136"],"abstract_inverted_index":{"Abstract":[0],"Data":[1],"quality":[2,68,90,141,157],"is":[3,70,143],"crucial":[4],"for":[5,17,93,104,122],"training":[6],"accurate,":[7],"unbiased,":[8],"and":[9,33,49,77,87,101,119,183],"trustworthy":[10],"machine":[11],"learning":[12],"models":[13,36],"as":[14,16,96,126,169],"well":[15],"their":[18],"correct":[19],"evaluation.":[20],"Recent":[21],"work,":[22],"however,":[23],"has":[24,61],"shown":[25],"that":[26],"even":[27],"popular":[28],"datasets":[29,76,118],"used":[30],"to":[31,56,63],"train":[32],"evaluate":[34],"state-of-the-art":[35],"contain":[37],"a":[38,110],"non-negligible":[39],"amount":[40],"of":[41,112,149,164,166],"erroneous":[42],"annotations,":[43,136],"biases,":[44],"or":[45,131,155],"artifacts.":[46],"While":[47],"practices":[48,92],"guidelines":[50],"regarding":[51],"dataset":[52,94],"creation":[53,95],"projects":[54],"exist,":[55],"our":[57],"knowledge,":[58],"large-scale":[59],"analysis":[60,173],"yet":[62],"be":[64],"performed":[65],"on":[66],"how":[67,140],"management":[69,91,142],"conducted":[71,144],"when":[72,179],"creating":[73],"natural":[74],"language":[75],"whether":[78],"these":[79,135],"recommendations":[80],"are":[81],"followed.":[82],"Therefore,":[83],"we":[84,108,137,160],"first":[85],"survey":[86],"summarize":[88],"recommended":[89],"described":[97],"in":[98,145],"the":[99,150,162,167],"literature":[100],"provide":[102],"suggestions":[103],"applying":[105],"them.":[106],"Then,":[107],"compile":[109],"corpus":[111],"591":[113],"scientific":[114],"publications":[115,152],"introducing":[116],"text":[117],"annotate":[120],"it":[121],"quality-related":[123],"aspects,":[124],"such":[125],"annotator":[127],"management,":[128],"agreement,":[129],"adjudication,":[130],"data":[132],"validation.":[133],"Using":[134],"then":[138],"analyze":[139],"practice.":[146],"A":[147],"majority":[148],"annotated":[151],"apply":[153],"good":[154],"excellent":[156],"management.":[158],"However,":[159],"deem":[161],"effort":[163],"30%":[165],"studies":[168],"only":[170],"subpar.":[171],"Our":[172],"also":[174],"shows":[175],"common":[176],"errors,":[177],"especially":[178],"using":[180],"inter-annotator":[181],"agreement":[182],"computing":[184],"annotation":[185],"error":[186],"rates.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}