{"id":"https://openalex.org/W4385724447","doi":"https://doi.org/10.1108/jd-03-2023-0055","title":"Digitizing and parsing semi-structured historical administrative documents from the\u00a0G.I. Bill mortgage guarantee program","display_name":"Digitizing and parsing semi-structured historical administrative documents from the\u00a0G.I. Bill mortgage guarantee program","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385724447","doi":"https://doi.org/10.1108/jd-03-2023-0055"},"language":"en","primary_location":{"id":"doi:10.1108/jd-03-2023-0055","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2023-0055","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/JD-03-2023-0055/full/pdf?title=digitizing-and-parsing-semi-structured-historical-administrative-documents-from-the-gi-bill-mortgage-guarantee-program","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.emerald.com/insight/content/doi/10.1108/JD-03-2023-0055/full/pdf?title=digitizing-and-parsing-semi-structured-historical-administrative-documents-from-the-gi-bill-mortgage-guarantee-program","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023705928","display_name":"Sara Lafia","orcid":"https://orcid.org/0000-0002-5896-7295"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sara Lafia","raw_affiliation_strings":["ICPSR, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-5896-7295","affiliations":[{"raw_affiliation_string":"ICPSR, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090777955","display_name":"David Bleckley","orcid":"https://orcid.org/0000-0001-7715-4348"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Bleckley","raw_affiliation_strings":["ICPSR, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0001-7715-4348","affiliations":[{"raw_affiliation_string":"ICPSR, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108262868","display_name":"J. Trent Alexander","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Trent Alexander","raw_affiliation_strings":["ICPSR, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICPSR, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023705928"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58992195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"79","issue":"7","first_page":"225","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9905999898910522,"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":0.8075026273727417},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.8037381172180176},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7430886626243591},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.549928605556488},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5384094715118408},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46853700280189514},{"id":"https://openalex.org/keywords/loan","display_name":"Loan","score":0.439802348613739},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4343382716178894},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3908994793891907},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3025745749473572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24860581755638123},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12168502807617188},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.10901707410812378},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10260960459709167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075026273727417},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.8037381172180176},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7430886626243591},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.549928605556488},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5384094715118408},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46853700280189514},{"id":"https://openalex.org/C2777764128","wikidata":"https://www.wikidata.org/wiki/Q189539","display_name":"Loan","level":2,"score":0.439802348613739},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4343382716178894},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3908994793891907},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3025745749473572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24860581755638123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12168502807617188},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.10901707410812378},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10260960459709167},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1108/jd-03-2023-0055","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2023-0055","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/JD-03-2023-0055/full/pdf?title=digitizing-and-parsing-semi-structured-historical-administrative-documents-from-the-gi-bill-mortgage-guarantee-program","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/176363","is_oa":true,"landing_page_url":"http://deepblue.lib.umich.edu/bitstream/2027.42/176363/1/GI%20Bill%20digitization%20technical%20paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.7302/7212","is_oa":true,"landing_page_url":"https://doi.org/10.7302/7212","pdf_url":null,"source":{"id":"https://openalex.org/S7407053136","display_name":"University of Michigan Library","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":"article"}],"best_oa_location":{"id":"doi:10.1108/jd-03-2023-0055","is_oa":true,"landing_page_url":"https://doi.org/10.1108/jd-03-2023-0055","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/JD-03-2023-0055/full/pdf?title=digitizing-and-parsing-semi-structured-historical-administrative-documents-from-the-gi-bill-mortgage-guarantee-program","source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385724447.pdf","grobid_xml":"https://content.openalex.org/works/W4385724447.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2049686595","https://openalex.org/W2056397490","https://openalex.org/W2067995429","https://openalex.org/W2069691298","https://openalex.org/W2072393922","https://openalex.org/W2078090947","https://openalex.org/W2103470711","https://openalex.org/W2118736563","https://openalex.org/W2151765755","https://openalex.org/W2154547898","https://openalex.org/W2164371886","https://openalex.org/W2787494303","https://openalex.org/W2912132818","https://openalex.org/W3003711898","https://openalex.org/W3004051332","https://openalex.org/W3043552410","https://openalex.org/W3043995050","https://openalex.org/W3093938929","https://openalex.org/W3096258834","https://openalex.org/W3202466114","https://openalex.org/W3208962647","https://openalex.org/W4207066626","https://openalex.org/W4285500013","https://openalex.org/W6949549905","https://openalex.org/W7075269551"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W4322582183","https://openalex.org/W2592115649","https://openalex.org/W1937392525","https://openalex.org/W2347632764"],"abstract_inverted_index":{"Purpose":[0],"Many":[1],"libraries":[2],"and":[3,32,79,135,143,166,169,195,233,286,308,333,360],"archives":[4],"maintain":[5],"collections":[6,28,36],"of":[7,60,87,96,101,115,123,145,150,155,171,212,225,274,304,319,345],"research":[8,340],"documents,":[9],"such":[10,48],"as":[11,49,105],"administrative":[12,88,275,320],"records,":[13],"with":[14,252,259],"paper-based":[15,27,118],"formats":[16],"that":[17,363],"limit":[18],"the":[19,58,69,92,97,106,121,141,146,148,151,153,156,167,172,175,208,220,244,253,265,272,287,302,311,314,324,334,343,351,354,358,361],"documents'":[20],"access":[21],"to":[22,43,56,82,91,129,131,189,198,242,277,296,323,331],"in-person":[23],"use.":[24],"Digitization":[25],"transforms":[26],"into":[29,54,342],"more":[30,163],"accessible":[31],"analyzable":[33],"formats.":[34],"As":[35],"are":[37],"digitized,":[38],"there":[39],"is":[40,293],"an":[41],"opportunity":[42],"incorporate":[44],"deep":[45,80],"learning":[46,81],"techniques,":[47],"Document":[50],"Image":[51],"Analysis":[52],"(DIA),":[53],"workflows":[55],"increase":[57],"usability":[59],"information":[61,181],"extracted":[62,179],"from":[63,120,127,182,349],"archival":[64,298],"documents.":[65],"This":[66],"paper":[67],"describes":[68],"authors'":[70,291],"approach":[71],"using":[72,250],"digital":[73,85,305,316],"scanning,":[74,306],"optical":[75],"character":[76,210,221],"recognition":[77,236],"(OCR)":[78],"create":[83,190],"a":[84,113,133,191,280],"archive":[86],"records":[89,119,139,186,276,321,338],"related":[90,322],"mortgage":[93,327],"guarantee":[94,328],"program":[95,329],"Servicemen's":[98],"Readjustment":[99],"Act":[100],"1944,":[102],"also":[103],"known":[104],"G.I.":[107,124,325],"Bill.":[108],"Design/methodology/approach":[109],"The":[110,177,205,216,238,290],"authors":[111,178,206,217,239,266,312],"used":[112],"collection":[114],"25,744":[116],"semi-structured":[117],"administration":[122],"Bill":[125,326],"Mortgages":[126],"1946":[128],"1954":[130],"develop":[132],"digitization":[134,273,299],"processing":[136],"workflow.":[137],"These":[138,337],"include":[140],"name":[142,168],"city":[144],"mortgagor,":[147],"amount":[149],"mortgage,":[152],"location":[154,170],"Reconstruction":[157],"Finance":[158],"Corporation":[159],"agent,":[160],"one":[161],"or":[162],"identification":[164],"numbers":[165],"bank":[173],"handling":[174],"loan.":[176],"structured":[180,247,281],"these":[183],"scanned":[184],"historical":[185],"in":[187],"order":[188],"tabular":[192],"data":[193,202,282],"file":[194,318],"link":[196],"them":[197],"other":[199,297],"authoritative":[200],"individual-level":[201],"sources.":[203],"Findings":[204],"compared":[207,219],"flexible":[209],"accuracy":[211],"five":[213],"OCR":[214,307],"methods.":[215],"then":[218],"error":[222],"rate":[223],"(CER)":[224],"three":[226],"text":[227,248],"extraction":[228],"approaches":[229],"(regular":[230],"expressions,":[231],"DIA":[232,251,269,309],"named":[234],"entity":[235],"(NER)).":[237],"were":[240],"able":[241],"obtain":[243],"highest":[245],"quality":[246],"output":[249],"Layout":[254],"Parser":[255],"toolkit":[256],"by":[257,357],"post-processing":[258],"regular":[260],"expressions.":[261],"Through":[262,301],"this":[263],"project,":[264],"demonstrate":[267],"how":[268],"can":[270],"improve":[271],"automatically":[278],"produce":[279],"resource":[283],"for":[284],"researchers":[285,332],"public.":[288,336],"Originality/value":[289],"workflow":[292],"readily":[294],"transferable":[295],"projects.":[300],"use":[303],"processes,":[310],"created":[313],"first":[315],"microdata":[317],"available":[330],"general":[335],"offer":[339],"insights":[341],"lives":[344],"veterans":[346],"who":[347],"benefited":[348],"loans,":[350],"impacts":[352],"on":[353],"communities":[355],"built":[356],"loans":[359],"institutions":[362],"implemented":[364],"them.":[365]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
