{"id":"https://openalex.org/W4395689664","doi":"https://doi.org/10.1145/3603287.3651200","title":"Challenges of Automatic Document Processing with Historical Data","display_name":"Challenges of Automatic Document Processing with Historical Data","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4395689664","doi":"https://doi.org/10.1145/3603287.3651200"},"language":"en","primary_location":{"id":"doi:10.1145/3603287.3651200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603287.3651200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5095913604","display_name":"Katerina Vilkomir","orcid":"https://orcid.org/0009-0006-2907-4494"},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katerina Vilkomir","raw_affiliation_strings":["East Carolina University, Greenville, North Carolina, USA"],"raw_orcid":"https://orcid.org/0009-0006-2907-4494","affiliations":[{"raw_affiliation_string":"East Carolina University, Greenville, North Carolina, USA","institution_ids":["https://openalex.org/I186335123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059305373","display_name":"Nic Herndon","orcid":"https://orcid.org/0000-0001-9712-148X"},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nic Herndon","raw_affiliation_strings":["East Carolina University, Greenville, North Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0001-9712-148X","affiliations":[{"raw_affiliation_string":"East Carolina University, Greenville, North Carolina, USA","institution_ids":["https://openalex.org/I186335123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5095913604"],"corresponding_institution_ids":["https://openalex.org/I186335123"],"apc_list":null,"apc_paid":null,"fwci":7.4785,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96179905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9847999811172485,"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":0.9836999773979187,"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/computer-science","display_name":"Computer science","score":0.7358068227767944},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4612210690975189},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3308870196342468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358068227767944},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4612210690975189},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3308870196342468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603287.3651200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603287.3651200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W976146978","https://openalex.org/W1589080406","https://openalex.org/W1981986349","https://openalex.org/W2011743827","https://openalex.org/W2144772486","https://openalex.org/W2149961050","https://openalex.org/W2559509773","https://openalex.org/W2956328330","https://openalex.org/W2980626131","https://openalex.org/W2986829274","https://openalex.org/W3001206875","https://openalex.org/W3090423411","https://openalex.org/W3092694106","https://openalex.org/W3178709966","https://openalex.org/W4250773508","https://openalex.org/W4293796968","https://openalex.org/W4385724447","https://openalex.org/W4391320418"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"There":[0],"are":[1],"many":[2],"challenges":[3,69],"in":[4],"implementing":[5],"a":[6,71,94],"system":[7],"for":[8,36,48],"automatic":[9],"document":[10],"processing":[11],"of":[12,73,96,110],"historical":[13,113],"data.":[14,114],"In":[15],"this":[16],"paper,":[17],"we":[18],"describe":[19],"several":[20],"challenges,":[21],"such":[22,76],"as":[23,77],"poor":[24],"data":[25,35],"quality":[26],"and":[27,31,41,61,86,89,99,102,108],"inconsistency,":[28],"different":[29],"language":[30,82],"structure":[32],"changes,":[33],"limited":[34],"training":[37],"machine":[38,84],"learning":[39],"models,":[40],"sensitive":[42],"content":[43],"that":[44],"requires":[45,70],"special":[46],"handling":[47],"privacy":[49],"reasons.":[50],"We":[51],"show":[52],"how":[53],"important":[54],"it":[55],"is":[56],"to":[57,104],"solve":[58],"these":[59,68],"problems":[60],"what":[62],"impact":[63],"they":[64],"could":[65],"have.":[66],"Overcoming":[67],"combination":[72,95],"advanced":[74],"technologies,":[75],"optical":[78],"character":[79],"recognition,":[80],"natural":[81],"processing,":[83],"learning,":[85],"human":[87],"support":[88],"expertise.":[90],"This":[91],"often":[92],"involves":[93],"automated":[97],"algorithms":[98],"manual":[100],"verification":[101],"correction":[103],"ensure":[105],"the":[106,111],"accuracy":[107],"reliability":[109],"processed":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}