{"id":"https://openalex.org/W2134376194","doi":"https://doi.org/10.1145/1600193.1600202","title":"Automated re-typesetting, indexing and contentenhancement for scanned marriage registers","display_name":"Automated re-typesetting, indexing and contentenhancement for scanned marriage registers","publication_year":2009,"publication_date":"2009-09-16","ids":{"openalex":"https://openalex.org/W2134376194","doi":"https://doi.org/10.1145/1600193.1600202","mag":"2134376194"},"language":"en","primary_location":{"id":"doi:10.1145/1600193.1600202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nottingham-repository.worktribe.com/preview/1013600/eprints-paper2009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064560699","display_name":"David F. Brailsford","orcid":null},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David F. Brailsford","raw_affiliation_strings":["University of Nottingham, NOTTINGHAM, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham, NOTTINGHAM, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064560699"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":null,"apc_paid":null,"fwci":0.6022,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64892086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9800000190734863,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9269000291824341,"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":0.7861402034759521},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6146571636199951},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5815672278404236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5056302547454834},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.49074113368988037},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4759801924228668},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.4617242217063904},{"id":"https://openalex.org/keywords/unix","display_name":"Unix","score":0.44746360182762146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38199734687805176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33218663930892944},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1792682707309723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861402034759521},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6146571636199951},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5815672278404236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5056302547454834},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.49074113368988037},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4759801924228668},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.4617242217063904},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.44746360182762146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38199734687805176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33218663930892944},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1792682707309723}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1600193.1600202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:nottingham-repository.worktribe.com:1013594","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/1013594","pdf_url":"https://nottingham-repository.worktribe.com/preview/1013600/eprints-paper2009.pdf","source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},{"id":"pmh:oai:eprints.nottingham.ac.uk:28117","is_oa":true,"landing_page_url":"http://eprints.nottingham.ac.uk/28117/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402014","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:nottingham-repository.worktribe.com:1013594","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/1013594","pdf_url":"https://nottingham-repository.worktribe.com/preview/1013600/eprints-paper2009.pdf","source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4300000071525574,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2134376194.pdf","grobid_xml":"https://content.openalex.org/works/W2134376194.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W197556408","https://openalex.org/W1487895014","https://openalex.org/W2110888112","https://openalex.org/W2131411374","https://openalex.org/W2155133464"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W4252960523","https://openalex.org/W1529821365","https://openalex.org/W2135486207","https://openalex.org/W1499611046","https://openalex.org/W3024420453","https://openalex.org/W2571087188"],"abstract_inverted_index":{"For":[0],"much":[1],"of":[2,55,85,88,97,115,126,134,155,162,177,191,218,242],"England":[3],"and":[4,20,71,171,211,222,228],"Wales":[5],"marriage":[6,15,62,220],"registers":[7,32,63],"began":[8],"to":[9,45,60,72,94,130,148,182,208,256],"be":[10,250],"kept":[11,34],"in":[12,21,35,81,199],"1537.":[13],"The":[14,99,124,231],"details":[16],"were":[17,33],"recorded":[18],"locally,":[19],"longhand,":[22],"until":[23],"1st":[24],"July":[25],"1837,":[26],"when":[27],"central":[28],"records":[29],"began.":[30],"All":[31],"the":[36,41,52,82,89,95,120,127,151,156,164,185,189,192,206,216,219,240,258],"local":[37],"parish":[38],"church.":[39],"In":[40],"period":[42],"from":[43,106,119],"1896":[44],"1922":[46],"an":[47,79,197],"attempt":[48],"was":[49,102,129,194],"made,":[50],"by":[51],"Phillimore":[53,91],"company":[54],"London,":[56],"using":[57,167,261],"volunteer":[58],"help,":[59],"transcribe":[61],"for":[64,235],"as":[65,69,141,159],"many":[66],"English":[67],"parishes":[68],"possible":[70,147],"have":[73],"them":[74],"printed.":[75],"This":[76,214],"paper":[77],"describes":[78],"experiment":[80,128,232],"automated":[83],"re-typesetting":[84,165,190],"Volume":[86],"2":[87],"15-volume":[90],"series":[92,176],"relating":[93],"county":[96],"Derbyshire.":[98],"source":[100],"material":[101,260],"plain":[103],"text":[104,193],"derived":[105],"running":[107],"Optical":[108],"Character":[109],"Recognition":[110],"(OCR)":[111],"on":[112,150,205],"a":[113,160,203],"set":[114],"page":[116],"scans":[117],"taken":[118],"original":[121],"printed":[122,259],"volume.":[123],"aim":[125],"avoid":[131],"any":[132],"idea":[133],"labour-intensive":[135],"page-by-page":[136],"rebuilding":[137],"with":[138,245],"tools":[139,180],"such":[140],"Acrobat":[142],"Capture.":[143],"Instead,":[144],"it":[145],"proved":[146],"capitalise":[149],"regular,":[152],"tabular,":[153],"structure":[154],"Register":[157],"pages":[158],"means":[161],"automating":[163],"process,":[166],"UNIX":[168],"troff":[169],"software":[170,179],"its":[172],"tbl":[173],"preprocessor.":[174],"A":[175],"simple":[178],"helped":[181],"bring":[183],"about":[184],"OCR-to-troff":[186],"transformation.":[187],"However,":[188],"not":[195],"just":[196],"end":[198],"itself":[200],"but,":[201],"additionally,":[202],"step":[204],"way":[207],"content":[209,212],"enhancement":[210],"repurposing.":[213],"included":[215],"indexing":[217],"entries":[221],"their":[223],"potential":[224],"transformation":[225],"into":[226],"XML":[227],"GEDCOM":[229],"notations.":[230],"has":[233],"shown,":[234],"highly":[236],"regular":[237],"material,":[238],"that":[239],"efforts":[241],"one":[243],"programmer,":[244],"suitable":[246],"low-level":[247],"tools,":[248],"can":[249],"far":[251],"more":[252],"effective":[253],"than":[254],"attempting":[255],"recreate":[257],"WYSIWYG":[262],"software.":[263]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
