{"id":"https://openalex.org/W2739643355","doi":"https://doi.org/10.18653/v1/p17-1107","title":"Detecting annotation noise in automatically labelled data","display_name":"Detecting annotation noise in automatically labelled data","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739643355","doi":"https://doi.org/10.18653/v1/p17-1107","mag":"2739643355"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1107","pdf_url":"https://www.aclweb.org/anthology/P17-1107.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064974921","display_name":"Ines Rehbein","orcid":"https://orcid.org/0000-0002-9615-6389"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ines Rehbein","raw_affiliation_strings":["Leibniz Science Campus \"Empirical Linguistics and Computational Language Modeling\"","IDS Mannheim/University of Heidelberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Science Campus \"Empirical Linguistics and Computational Language Modeling\"","institution_ids":[]},{"raw_affiliation_string":"IDS Mannheim/University of Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011827545","display_name":"Josef Ruppenhofer","orcid":"https://orcid.org/0000-0002-8662-7618"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef Ruppenhofer","raw_affiliation_strings":["IDS Mannheim/University of Heidelberg, Germany","Leibniz Science Campus \"Empirical Linguistics and Computational Language Modeling\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS Mannheim/University of Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Leibniz Science Campus \"Empirical Linguistics and Computational Language Modeling\"","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":3.7172,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94599839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1160","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8284687995910645},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8072114586830139},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5879902243614197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5515013337135315},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5490928888320923},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5446663498878479},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5176289677619934},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4914900064468384},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44156765937805176},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4398888051509857},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.41756486892700195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33573293685913086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284687995910645},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8072114586830139},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5879902243614197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515013337135315},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5490928888320923},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5446663498878479},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5176289677619934},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4914900064468384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44156765937805176},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4398888051509857},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41756486892700195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33573293685913086},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p17-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1107","pdf_url":"https://www.aclweb.org/anthology/P17-1107.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:ids-pub.bsz-bw.de:8034","is_oa":false,"landing_page_url":"https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/8034","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1107","pdf_url":"https://www.aclweb.org/anthology/P17-1107.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G6604464234","display_name":null,"funder_award_id":"SAS-2015","funder_id":"https://openalex.org/F4320334763","funder_display_name":"Leibniz-Gemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739643355.pdf","grobid_xml":"https://content.openalex.org/works/W2739643355.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W202361227","https://openalex.org/W1522263329","https://openalex.org/W1570013475","https://openalex.org/W1970381522","https://openalex.org/W1986330201","https://openalex.org/W2006873020","https://openalex.org/W2021664962","https://openalex.org/W2047477415","https://openalex.org/W2049633694","https://openalex.org/W2076018040","https://openalex.org/W2080021732","https://openalex.org/W2091950237","https://openalex.org/W2125943921","https://openalex.org/W2127937179","https://openalex.org/W2144578941","https://openalex.org/W2146849125","https://openalex.org/W2155870214","https://openalex.org/W2159133636","https://openalex.org/W2160986985","https://openalex.org/W2250553586","https://openalex.org/W2250872259","https://openalex.org/W2251272155","https://openalex.org/W2251818274","https://openalex.org/W2399720833","https://openalex.org/W2403681572","https://openalex.org/W2540392403","https://openalex.org/W2570764145","https://openalex.org/W2578406773","https://openalex.org/W2952087486","https://openalex.org/W2964090065","https://openalex.org/W4310738704"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W2358294942","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"We":[0,36],"introduce":[1],"a":[2,53],"method":[3,24,65],"for":[4],"error":[5],"detection":[6],"in":[7,45,48,52],"automatically":[8],"annotated":[9],"text,":[10],"aimed":[11],"at":[12,20],"supporting":[13],"the":[14,60],"creation":[15],"of":[16],"high-quality":[17],"language":[18],"resources":[19],"affordable":[21],"cost.":[22],"Our":[23],"combines":[25],"an":[26],"unsupervised":[27],"generative":[28],"model":[29],"with":[30,72],"human":[31],"supervision":[32],"from":[33],"active":[34],"learning.":[35],"test":[37],"our":[38,64],"approach":[39],"on":[40],"in-domain":[41],"and":[42,51,75],"out-of-domain":[43],"data":[44],"two":[46],"languages,":[47],"AL":[49],"simulations":[50],"real":[54],"world":[55],"setting.":[56],"For":[57],"all":[58],"settings,":[59],"results":[61],"show":[62],"that":[63],"is":[66],"able":[67],"to":[68],"detect":[69],"annotation":[70],"errors":[71],"high":[73,76],"precision":[74],"recall.":[77]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}