{"id":"https://openalex.org/W2951357757","doi":"https://doi.org/10.18653/v1/p19-1157","title":"Historical Text Normalization with Delayed Rewards","display_name":"Historical Text Normalization with Delayed Rewards","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951357757","doi":"https://doi.org/10.18653/v1/p19-1157","mag":"2951357757"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1157","pdf_url":"https://www.aclweb.org/anthology/P19-1157.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1157.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028331418","display_name":"Simon Flachs","orcid":null},"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":false,"raw_author_name":"Simon Flachs","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"]}]},{"author_position":"middle","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":false,"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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"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":false,"raw_author_name":"Anders S\u00f8gaard","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":[],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":0.7049,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7757661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1614","last_page":"1619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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":0.744020938873291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.611960768699646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3772197961807251},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.11397913098335266},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.07809820771217346}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.744020938873291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611960768699646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3772197961807251},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.11397913098335266},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.07809820771217346}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p19-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1157","pdf_url":"https://www.aclweb.org/anthology/P19-1157.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f56b041d-6814-4f9a-9d7a-246e533680a5","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/f56b041d-6814-4f9a-9d7a-246e533680a5","pdf_url":"https://curis.ku.dk/ws/files/239617715/Oa_Historical_Text_Normalization_with_Delayed_Rewards.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":"Flachs , S , Bollmann , M & S\u00f8gaard , A 2019 , Historical Text Normalization with Delayed Rewards . in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics , pp. 1614-1619 , 57th Annual Meeting of the Association for Computational Linguistics , Florence, Italy , 01/07/2019 . https://doi.org/10.18653/v1/P19-1157","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f56b041d-6814-4f9a-9d7a-246e533680a5","is_oa":true,"landing_page_url":"https://curis.ku.dk/portal/da/publications/historical-text-normalization-with-delayed-rewards(f56b041d-6814-4f9a-9d7a-246e533680a5).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/p19-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1157","pdf_url":"https://www.aclweb.org/anthology/P19-1157.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8880515317","display_name":"Morphologically-informed representations for natural language processing","funder_award_id":"845995","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951357757.pdf","grobid_xml":"https://content.openalex.org/works/W2951357757.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W2119717200","https://openalex.org/W2122262818","https://openalex.org/W2133564696","https://openalex.org/W2138238723","https://openalex.org/W2155027007","https://openalex.org/W2156718681","https://openalex.org/W2176263492","https://openalex.org/W2266080033","https://openalex.org/W2741138687","https://openalex.org/W2808154809","https://openalex.org/W2945958591","https://openalex.org/W2950176361","https://openalex.org/W2952264928","https://openalex.org/W2963069632","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2963456262","https://openalex.org/W2963463964","https://openalex.org/W2963715460","https://openalex.org/W2964308564","https://openalex.org/W2982630078","https://openalex.org/W4210706177","https://openalex.org/W4293543602","https://openalex.org/W4297785678","https://openalex.org/W4299300709","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197"],"abstract_inverted_index":{"Training":[0],"neural":[1],"sequence-to-sequence":[2],"models":[3],"with":[4],"simple":[5],"token-level":[6],"log-likelihood":[7],"is":[8],"now":[9],"a":[10],"standard":[11],"approach":[12],"to":[13,54,66],"historical":[14,38],"text":[15,39],"normalization,":[16],"albeit":[17],"often":[18],"outperformed":[19],"by":[20],"phrasebased":[21],"models.":[22],"Policy":[23,60],"gradient":[24,51,61],"training":[25],"enables":[26],"direct":[27],"optimization":[28],"for":[29,70],"exact":[30],"matches,":[31],"and":[32],"while":[33],"the":[34,58],"small":[35],"datasets":[36],"in":[37,63],"normalization":[40],"are":[41],"prohibitive":[42],"of":[43],"from-scratch":[44],"reinforcement":[45],"learning,":[46],"we":[47],"show":[48],"that":[49],"policy":[50],"fine-tuning":[52],"leads":[53,65],"significant":[55],"improvements":[56],"across":[57],"board.":[59],"training,":[62],"particular,":[64],"more":[67],"accurate":[68],"normalizations":[69],"long":[71],"or":[72],"unseen":[73],"words.":[74]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}