{"id":"https://openalex.org/W3203792196","doi":"https://doi.org/10.1007/978-3-030-86331-9_48","title":"Data Centric Domain Adaptation for Historical&#13;\\nText with OCR Errors","display_name":"Data Centric Domain Adaptation for Historical&#13;\\nText with OCR Errors","publication_year":2021,"publication_date":"2021-09-02","ids":{"openalex":"https://openalex.org/W3203792196","doi":"https://doi.org/10.1007/978-3-030-86331-9_48","mag":"3203792196"},"language":"en","primary_location":{"id":"pmh:oai:epub.ub.uni-muenchen.de:92207","is_oa":false,"landing_page_url":"https://epub.ub.uni-muenchen.de/92207/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},"type":"book-chapter","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005379598","display_name":"Luisa M\u00e4rz","orcid":"https://orcid.org/0000-0003-4542-2437"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]},{"id":"https://openalex.org/I1319473763","display_name":"Volkswagen Group (Germany)","ror":"https://ror.org/01f3bhg26","country_code":"DE","type":"company","lineage":["https://openalex.org/I1319473763"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["AT","DE"],"is_corresponding":false,"raw_author_name":"Marz, Luisa","raw_affiliation_strings":["Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany","Digital Philology, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria","NLP Expert Center, Data:Lab, Volkswagen AG, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Digital Philology, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"NLP Expert Center, Data:Lab, Volkswagen AG, Munich, Germany","institution_ids":["https://openalex.org/I1319473763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024609215","display_name":"Stefan Schweter","orcid":"https://orcid.org/0000-0002-7190-2090"},"institutions":[{"id":"https://openalex.org/I4210138660","display_name":"Bavarian State Library","ror":"https://ror.org/031h71w90","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210138660"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schweter, Stefan","raw_affiliation_strings":["Bayerische Staatsbibliothek M\u00fcnchen, Digital Library/Munich Digitization Center, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bayerische Staatsbibliothek M\u00fcnchen, Digital Library/Munich Digitization Center, Munich, Germany","institution_ids":["https://openalex.org/I4210138660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042212425","display_name":"Nina Poerner","orcid":"https://orcid.org/0000-0002-1292-7052"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Poerner, Nina","raw_affiliation_strings":["Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046895021","display_name":"Benjamin Roth","orcid":"https://orcid.org/0000-0003-0362-0267"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roth, Benjamin","raw_affiliation_strings":["Digital Philology, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Philology, Research Group Data Mining and Machine Learning, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071144367","display_name":"Hinrich Sch\u00fctze","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sch\u00fctze, Hinrich","raw_affiliation_strings":["Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, Ludwig Maximilian University, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Llad\u00f3s, J.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Llad\u00f3s, J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lopresti, D.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lopresti, D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Uchida, S.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uchida, S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T13629","display_name":"Text Readability and Simplification","score":0.9370999932289124,"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":0.8804689645767212},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7991268038749695},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7942663431167603},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6267461776733398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5204025506973267},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.5070195198059082},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.497024804353714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.485705703496933},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4621840715408325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3898370862007141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804689645767212},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7991268038749695},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7942663431167603},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6267461776733398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5204025506973267},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.5070195198059082},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.497024804353714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.485705703496933},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4621840715408325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3898370862007141},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:epub.ub.uni-muenchen.de:92207","is_oa":false,"landing_page_url":"https://epub.ub.uni-muenchen.de/92207/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325350","display_name":"Henan Institute of Science and Technology","ror":"https://ror.org/0578f1k82"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1970026646","https://openalex.org/W2032223184","https://openalex.org/W2057399676","https://openalex.org/W2096765155","https://openalex.org/W2120844411","https://openalex.org/W2133485975","https://openalex.org/W2144578941","https://openalex.org/W2296283641","https://openalex.org/W2493916176","https://openalex.org/W2573560226","https://openalex.org/W2579840722","https://openalex.org/W2787747535","https://openalex.org/W2880875857","https://openalex.org/W2915429162","https://openalex.org/W2940152587","https://openalex.org/W2945808722","https://openalex.org/W2946119234","https://openalex.org/W2946558277","https://openalex.org/W2963341956","https://openalex.org/W2970119519","https://openalex.org/W2971301409","https://openalex.org/W3004299970","https://openalex.org/W3049158684","https://openalex.org/W3084721699","https://openalex.org/W3095348722","https://openalex.org/W3095353111","https://openalex.org/W3114610051"],"related_works":["https://openalex.org/W3199871245","https://openalex.org/W2915436880","https://openalex.org/W3128275854","https://openalex.org/W4394775207","https://openalex.org/W2573722871","https://openalex.org/W4310925487","https://openalex.org/W3037747687","https://openalex.org/W4382318276","https://openalex.org/W3006421644","https://openalex.org/W4385567153"],"abstract_inverted_index":{"We":[0,54,83],"propose":[1,55],"new":[2],"methods":[3],"for":[4,15],"in-domain":[5,30,73],"and":[6,17,36,48,79,90],"cross-domain":[7,21,68],"Named":[8],"Entity":[9],"Recognition":[10],"(NER)":[11],"on":[12],"historical":[13],"data":[14,31,50],"Dutch":[16,91],"French.":[18],"For":[19],"the":[20,45,88],"case,":[22],"we":[23],"address":[24,49],"domain":[25,47,52],"shift":[26],"by":[27,39],"integrating":[28],"unsupervised":[29],"via":[32],"contextualized":[33],"string":[34],"embeddings;":[35],"OCR":[37,42,61],"errors":[38,43,62],"injecting":[40],"synthetic":[41],"into":[44],"source":[46],"centric":[51],"adaptation.":[53],"a":[56],"general":[57],"approach":[58],"to":[59],"imitate":[60],"in":[63],"arbitrary":[64],"input":[65],"data.":[66],"Our":[67],"as":[69,71],"well":[70],"our":[72],"results":[74],"outperform":[75],"several":[76],"strong":[77],"baselines":[78],"establish":[80],"state-of-the-art":[81],"results.":[82],"publish":[84],"preprocessed":[85],"versions":[86],"of":[87],"French":[89],"Europeana":[92],"NER":[93],"corpora.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
