{"id":"https://openalex.org/W2950176361","doi":"https://doi.org/10.18653/v1/n19-1389","title":"A Large-Scale Comparison of Historical Text Normalization Systems","display_name":"A Large-Scale Comparison of Historical Text Normalization Systems","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950176361","doi":"https://doi.org/10.18653/v1/n19-1389","mag":"2950176361"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n19-1389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1389","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/n19-1389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005438563","display_name":"Marcel Bollmann","orcid":"https://orcid.org/0000-0003-2598-8150"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Marcel Bollmann","raw_affiliation_strings":["Department of Computer Science University of Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005438563"],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":3.8062,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.94665973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3885","last_page":"3898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/normalization","display_name":"Normalization (sociology)","score":0.9030073881149292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8075265884399414},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.766877293586731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415648818016052},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5304293632507324},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4946264922618866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46324482560157776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40163326263427734},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0870794951915741}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9030073881149292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075265884399414},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.766877293586731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415648818016052},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5304293632507324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4946264922618866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46324482560157776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40163326263427734},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0870794951915741},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/n19-1389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1389","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.02036","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.02036","pdf_url":"https://arxiv.org/pdf/1904.02036","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/eb0e4063-f7e4-4145-97cf-d6f107ea69ad","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/eb0e4063-f7e4-4145-97cf-d6f107ea69ad","pdf_url":"https://curis.ku.dk/ws/files/239617833/OA_A_Large_Scale_Comparison_of_Historical_Text_Normalization_Systems.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Bollmann , M 2019 , A Large-Scale Comparison of Historical Text Normalization Systems . in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) . Association for Computational Linguistics , pp. 3885-3898 , 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 , Minneapolis , United States , 03/06/2019 . https://doi.org/10.18653/v1/N19-1389","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:DiVA.org:liu-197949","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-197949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400837","display_name":"DiVA (Linkoping University)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/eb0e4063-f7e4-4145-97cf-d6f107ea69ad","is_oa":true,"landing_page_url":"https://curis.ku.dk/portal/da/publications/a-largescale-comparison-of-historical-text-normalization-systems(eb0e4063-f7e4-4145-97cf-d6f107ea69ad).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/n19-1389","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1389","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W105720630","https://openalex.org/W130632585","https://openalex.org/W619445499","https://openalex.org/W629021723","https://openalex.org/W779297117","https://openalex.org/W1553878378","https://openalex.org/W1581712682","https://openalex.org/W1647671624","https://openalex.org/W1822791557","https://openalex.org/W1882181510","https://openalex.org/W1970252520","https://openalex.org/W1999111115","https://openalex.org/W2005613933","https://openalex.org/W2041532239","https://openalex.org/W2068844591","https://openalex.org/W2085809856","https://openalex.org/W2124807415","https://openalex.org/W2135716572","https://openalex.org/W2137416755","https://openalex.org/W2166005393","https://openalex.org/W2166084679","https://openalex.org/W2187123015","https://openalex.org/W2251164187","https://openalex.org/W2251463342","https://openalex.org/W2266080033","https://openalex.org/W2271671850","https://openalex.org/W2462051594","https://openalex.org/W2497478236","https://openalex.org/W2514031637","https://openalex.org/W2576894420","https://openalex.org/W2595715041","https://openalex.org/W2602867757","https://openalex.org/W2624926655","https://openalex.org/W2625023053","https://openalex.org/W2740433069","https://openalex.org/W2741138687","https://openalex.org/W2792296443","https://openalex.org/W2795467683","https://openalex.org/W2807629868","https://openalex.org/W2808154809","https://openalex.org/W2945958591","https://openalex.org/W2955906716","https://openalex.org/W2956146831","https://openalex.org/W2963260927","https://openalex.org/W2963285936","https://openalex.org/W2963715460","https://openalex.org/W2963805136","https://openalex.org/W2964343359","https://openalex.org/W2982630078","https://openalex.org/W4205269580","https://openalex.org/W4293543602","https://openalex.org/W4293864276"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W2780629932","https://openalex.org/W2591697403","https://openalex.org/W2775554247","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"There":[0],"is":[1],"no":[2],"consensus":[3],"on":[4,67],"the":[5,48,61,80],"state-of-the-art":[6],"approach":[7],"to":[8,42],"historical":[9,52],"text":[10,53],"normalization.":[11],"Many":[12],"techniques":[13],"have":[14,32,40],"been":[15],"proposed,":[16],"including":[17],"rule-based":[18],"methods,":[19,38],"distance":[20],"metrics,":[21],"character-based":[22],"statistical":[23],"machine":[24],"translation,":[25],"and":[26,39,64,86,93],"neural":[27],"encoder\u2013decoder":[28],"models,":[29],"but":[30],"studies":[31],"used":[33],"different":[34,36,43,88],"datasets,":[35],"evaluation":[37,89],"come":[41],"conclusions.":[44],"This":[45],"paper":[46],"presents":[47],"largest":[49],"study":[50],"of":[51,75,82],"normalization":[54,77],"done":[55],"so":[56],"far.":[57],"We":[58],"critically":[59],"survey":[60],"existing":[62],"literature":[63],"report":[65],"experiments":[66],"eight":[68],"languages,":[69],"comparing":[70],"systems":[71],"spanning":[72],"all":[73],"categories":[74],"proposed":[76],"techniques,":[78],"analysing":[79],"effect":[81],"training":[83],"data":[84],"quantity,":[85],"using":[87],"methods.":[90],"The":[91],"datasets":[92],"scripts":[94],"are":[95],"made":[96],"publicly":[97],"available.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2020-11-23T00:00:00"}