{"id":"https://openalex.org/W2926029148","doi":"https://doi.org/10.18653/v1/d19-6112","title":"Few-Shot and Zero-Shot Learning for Historical Text Normalization","display_name":"Few-Shot and Zero-Shot Learning for Historical Text Normalization","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2926029148","doi":"https://doi.org/10.18653/v1/d19-6112","mag":"2926029148"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6112","pdf_url":"https://www.aclweb.org/anthology/D19-6112.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6112.pdf","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"]},{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH","DK"],"is_corresponding":false,"raw_author_name":"Marcel Bollmann","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747436","display_name":"Natalia Korchagina","orcid":null},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Natalia Korchagina","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","University of zurich;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"University of zurich;","institution_ids":["https://openalex.org/I202697423"]}]},{"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"]},{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH","DK"],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen  Institute of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02478486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.989300012588501,"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/normalization","display_name":"Normalization (sociology)","score":0.7616962194442749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577031850814819},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.6544408798217773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6122775077819824},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.5611978769302368},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.524754524230957},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4974565804004669},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48343050479888916},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4652342200279236},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4214320778846741},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41506925225257874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39547020196914673},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09161418676376343}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7616962194442749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577031850814819},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.6544408798217773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122775077819824},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.5611978769302368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.524754524230957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4974565804004669},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48343050479888916},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4652342200279236},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4214320778846741},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41506925225257874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39547020196914673},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09161418676376343},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.18653/v1/d19-6112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6112","pdf_url":"https://www.aclweb.org/anthology/D19-6112.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:178438","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Bollmann, Marcel; Korchagina, Natalia; S\u00f8gaard, Anders  (2019). Few-Shot and Zero-Shot Learning for Historical Text Normalization.  In: Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), Hong Kong, 1 November 2019, ACL.","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:1903.04870","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.04870","pdf_url":"https://arxiv.org/pdf/1903.04870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2926029148","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.04870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:DiVA.org:liu-197948","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-197948","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/d2685bb8-5be9-4d48-870b-6e6d439b81fb","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/d2685bb8-5be9-4d48-870b-6e6d439b81fb","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-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bollmann , M , Korchagina , N & S\u00f8gaard , A 2019 , Few-Shot and Zero-Shot Learning for Historical Text Normalization . in Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019) . Association for Computational Linguistics , pp. 104-114 , 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo) , Hong Kong , China , 03/11/2019 . https://doi.org/10.18653/v1/D19-6112","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1903.04870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.04870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5167/uzh-178438","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-178438","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6112","pdf_url":"https://www.aclweb.org/anthology/D19-6112.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G2410353915","display_name":"Parsing low-resource languages and domains","funder_award_id":"313695","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"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/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2926029148.pdf","grobid_xml":"https://content.openalex.org/works/W2926029148.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W130632585","https://openalex.org/W629021723","https://openalex.org/W1553878378","https://openalex.org/W1614862348","https://openalex.org/W2251743902","https://openalex.org/W2271671850","https://openalex.org/W2462051594","https://openalex.org/W2514457011","https://openalex.org/W2550821151","https://openalex.org/W2573704241","https://openalex.org/W2576894420","https://openalex.org/W2592170186","https://openalex.org/W2624926655","https://openalex.org/W2741138687","https://openalex.org/W2748157908","https://openalex.org/W2792296443","https://openalex.org/W2807188009","https://openalex.org/W2807629868","https://openalex.org/W2808154809","https://openalex.org/W2945958591","https://openalex.org/W2950176361","https://openalex.org/W2955906716","https://openalex.org/W2956146831","https://openalex.org/W2962705709","https://openalex.org/W2962982474","https://openalex.org/W2963167917","https://openalex.org/W2963247703","https://openalex.org/W2963285936","https://openalex.org/W2963779652","https://openalex.org/W2963842982","https://openalex.org/W2963913768","https://openalex.org/W2963917673","https://openalex.org/W2964308564","https://openalex.org/W2982630078"],"related_works":["https://openalex.org/W3205719411","https://openalex.org/W3116459227","https://openalex.org/W3161622534","https://openalex.org/W3034785721","https://openalex.org/W3210277894","https://openalex.org/W2963943197","https://openalex.org/W3042509360","https://openalex.org/W3021669159","https://openalex.org/W3212893438","https://openalex.org/W2804107505","https://openalex.org/W3093833448","https://openalex.org/W3019510943","https://openalex.org/W3213451312","https://openalex.org/W3151507536","https://openalex.org/W3209452396","https://openalex.org/W3213415226","https://openalex.org/W3165998135","https://openalex.org/W2970229707","https://openalex.org/W2902697547","https://openalex.org/W2987878148"],"abstract_inverted_index":{"Historical":[0],"text":[1,49],"normalization":[2,50],"often":[3],"relies":[4],"on":[5],"small":[6],"training":[7,74,88],"datasets.":[8],"Recent":[9],"work":[10],"has":[11,29],"shown":[12],"that":[13,95],"multi-task":[14,43],"learning":[15,37,44,97],"can":[16],"lead":[17],"to":[18],"significant":[19,69],"improvements":[20,70,86],"by":[21],"exploiting":[22],"synergies":[23],"with":[24],"related":[25],"datasets,":[26],"but":[27,82,101],"there":[28],"been":[30],"no":[31,85],"systematic":[32],"study":[33],"of":[34],"different":[35],"multitask":[36],"architectures.":[38],"This":[39],"paper":[40],"evaluates":[41],"63":[42],"configurations":[45],"for":[46,76],"sequence-to-sequence-based":[47],"historical":[48],"across":[51,71],"ten":[52],"datasets":[53],"from":[54],"eight":[55],"languages,":[56],"using":[57],"autoencoding,":[58],"grapheme-tophoneme":[59],"mapping,":[60],"and":[61],"lemmatization":[62],"as":[63],"auxiliary":[64],"tasks.":[65],"We":[66,92],"observe":[67],"consistent,":[68],"languages":[72],"when":[73,87],"data":[75,89],"the":[77,99],"target":[78],"task":[79],"is":[80,90],"limited,":[81],"minimal":[83],"or":[84],"abundant.":[91],"also":[93],"show":[94],"zero-shot":[96],"outperforms":[98],"simple,":[100],"relatively":[102],"strong,":[103],"identity":[104],"baseline.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}