{"id":"https://openalex.org/W4221050583","doi":"https://doi.org/10.1017/s1351324922000110","title":"In-depth analysis of the impact of OCR errors on named entity recognition and linking","display_name":"In-depth analysis of the impact of OCR errors on named entity recognition and linking","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4221050583","doi":"https://doi.org/10.1017/s1351324922000110"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000110","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000110","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/6369935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046944392","display_name":"Ahmed Hamdi","orcid":"https://orcid.org/0000-0002-8964-2135"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ahmed Hamdi","raw_affiliation_strings":["University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072568748","display_name":"Elvys Linhares Pontes","orcid":"https://orcid.org/0000-0002-9571-5193"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Elvys Linhares Pontes","raw_affiliation_strings":["University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050406382","display_name":"Nicolas Sid\u00e8re","orcid":"https://orcid.org/0000-0001-6719-5007"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Sidere","raw_affiliation_strings":["University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063992777","display_name":"Micka\u00ebl Coustaty","orcid":"https://orcid.org/0000-0002-0123-439X"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Micka\u00ebl Coustaty","raw_affiliation_strings":["University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"University of La Rochelle, Laboratoire L3i, Facult\u00e9 des Sciences et Technologies, B\u00e2timent Pascal, Avenue Michel Cr\u00e9peau, 17042 La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046944392"],"corresponding_institution_ids":["https://openalex.org/I4403928318","https://openalex.org/I78744979"],"apc_list":null,"apc_paid":null,"fwci":4.5506,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9517259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":"2","first_page":"425","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T11719","display_name":"Data Quality and Management","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8651925325393677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8110795021057129},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7530028820037842},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6009947657585144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5238180756568909},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4544518291950226},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.42039021849632263},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4130891263484955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32414495944976807},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06712260842323303},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.05620008707046509}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8651925325393677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110795021057129},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7530028820037842},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6009947657585144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238180756568909},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4544518291950226},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.42039021849632263},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4130891263484955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32414495944976807},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06712260842323303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.05620008707046509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324922000110","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324922000110","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:6369935","is_oa":true,"landing_page_url":"https://zenodo.org/record/6369935","pdf_url":"https://zenodo.org/record/6369935","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Natural Language Engineering","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-03615997v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03615997","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Natural Language Engineering, 2022, 29 (2), pp.425-448. ⟨10.1017/S1351324922000110⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:6369935","is_oa":true,"landing_page_url":"https://zenodo.org/record/6369935","pdf_url":"https://zenodo.org/record/6369935","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Natural Language Engineering","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221050583.pdf"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W95925839","https://openalex.org/W791629831","https://openalex.org/W1541376310","https://openalex.org/W1541691357","https://openalex.org/W1552847225","https://openalex.org/W1568620938","https://openalex.org/W1580235436","https://openalex.org/W1843650355","https://openalex.org/W1854024133","https://openalex.org/W1941319617","https://openalex.org/W1964189668","https://openalex.org/W1976951044","https://openalex.org/W1976978162","https://openalex.org/W1977053705","https://openalex.org/W1985952313","https://openalex.org/W1989302571","https://openalex.org/W2002938383","https://openalex.org/W2011084371","https://openalex.org/W2020278455","https://openalex.org/W2022166150","https://openalex.org/W2025641162","https://openalex.org/W2032464653","https://openalex.org/W2040916592","https://openalex.org/W2053299703","https://openalex.org/W2068882115","https://openalex.org/W2069172670","https://openalex.org/W2077941393","https://openalex.org/W2078591799","https://openalex.org/W2098057544","https://openalex.org/W2098700435","https://openalex.org/W2100703899","https://openalex.org/W2112497803","https://openalex.org/W2131193876","https://openalex.org/W2144896964","https://openalex.org/W2153848201","https://openalex.org/W2163918411","https://openalex.org/W2250539671","https://openalex.org/W2251559320","https://openalex.org/W2296283641","https://openalex.org/W2493916176","https://openalex.org/W2504998667","https://openalex.org/W2612690371","https://openalex.org/W2612773933","https://openalex.org/W2771490691","https://openalex.org/W2806875270","https://openalex.org/W2888236192","https://openalex.org/W2896457183","https://openalex.org/W2900753330","https://openalex.org/W2912993660","https://openalex.org/W2921812231","https://openalex.org/W2950333738","https://openalex.org/W2952230511","https://openalex.org/W2962739339","https://openalex.org/W2962902328","https://openalex.org/W2963563735","https://openalex.org/W2963691861","https://openalex.org/W2963738950","https://openalex.org/W2967691513","https://openalex.org/W2968567788","https://openalex.org/W2984147501","https://openalex.org/W3012289950","https://openalex.org/W3033919759","https://openalex.org/W3046245238","https://openalex.org/W3096186608","https://openalex.org/W3098350697","https://openalex.org/W3101680040","https://openalex.org/W3105093672","https://openalex.org/W3136215575","https://openalex.org/W3178709966","https://openalex.org/W3199662997","https://openalex.org/W4230543443","https://openalex.org/W6600479677","https://openalex.org/W6634514995","https://openalex.org/W6680623264","https://openalex.org/W6683738474","https://openalex.org/W6748304040","https://openalex.org/W6778507337","https://openalex.org/W7047636377"],"related_works":["https://openalex.org/W2032007337","https://openalex.org/W2186562580","https://openalex.org/W1991513203","https://openalex.org/W3178467699","https://openalex.org/W2155874911","https://openalex.org/W1884363728","https://openalex.org/W4386977977","https://openalex.org/W2916255597","https://openalex.org/W3000685722","https://openalex.org/W4253099099"],"abstract_inverted_index":{"Abstract":[0],"Named":[1],"entities":[2],"(NEs)":[3],"are":[4,33,45,55],"among":[5],"the":[6,37,75,92,132,150,159,167,170,175],"most":[7,48,52],"relevant":[8],"type":[9],"of":[10,39,94,117,125,134,145,152],"information":[11],"that":[12,31,148],"can":[13],"be":[14],"used":[15],"to":[16,35,90,128,180],"properly":[17],"index":[18],"digital":[19,40],"documents":[20,54,119],"and":[21,102,123,154,163,174,184],"thus":[22],"easily":[23],"retrieve":[24],"them.":[25],"It":[26],"has":[27],"long":[28],"been":[29],"observed":[30],"NEs":[32],"key":[34],"accessing":[36],"contents":[38],"library":[41],"portals":[42],"as":[43],"they":[44],"contained":[46],"in":[47,130],"user":[49],"queries.":[50],"However,":[51],"digitized":[53],"indexed":[56],"through":[57],"their":[58],"optical":[59],"character":[60],"recognition":[61,100],"(OCRed)":[62],"version":[63],"which":[64],"include":[65],"numerous":[66],"errors.":[67],"Although":[68],"OCR":[69,79,95,126,135,146,171],"engines":[70],"have":[71],"considerably":[72,82],"improved":[73],"over":[74],"last":[76],"few":[77],"years,":[78],"errors":[80,96,147],"still":[81],"impact":[83,93,133,149],"document":[84],"access.":[85],"Previous":[86],"works":[87],"were":[88],"conducted":[89],"evaluate":[91],"on":[97,136,166],"named":[98,103,137],"entity":[99,104,138],"(NER)":[101],"linking":[105],"(NEL)":[106],"techniques":[107],"separately.":[108],"In":[109],"this":[110],"article,":[111],"we":[112],"experimented":[113],"with":[114,120],"a":[115,142],"variety":[116],"OCRed":[118],"different":[121],"levels":[122],"types":[124],"noise":[127],"assess":[129],"depth":[131],"processing.":[139],"We":[140,156],"provide":[141],"deep":[143],"analysis":[144],"performance":[151],"NER":[153,183],"NEL.":[155,185],"then":[157],"present":[158],"resulting":[160],"exhaustive":[161],"study":[162],"subsequent":[164],"recommendations":[165],"adequate":[168],"documents,":[169],"quality":[172],"levels,":[173],"post-OCR":[176],"correction":[177],"strategies":[178],"required":[179],"perform":[181],"reliable":[182]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}