{"id":"https://openalex.org/W2101793424","doi":"https://doi.org/10.1145/2595188.2595214","title":"Estimating and rating the quality of optically character recognised text","display_name":"Estimating and rating the quality of optically character recognised text","publication_year":2014,"publication_date":"2014-05-19","ids":{"openalex":"https://openalex.org/W2101793424","doi":"https://doi.org/10.1145/2595188.2595214","mag":"2101793424"},"language":"en","primary_location":{"id":"doi:10.1145/2595188.2595214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19608173/Alex_and_Burns_2014_Estimating_and_rating_the_quality.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043179000","display_name":"Beatrice Alex","orcid":"https://orcid.org/0000-0002-7279-1476"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Beatrice Alex","raw_affiliation_strings":["University of Edinburgh, Edinburgh, UK","University of Edinburgh, Edinburgh , UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh, Edinburgh , UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039675719","display_name":"John A. Burns","orcid":"https://orcid.org/0000-0002-2348-8438"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Burns","raw_affiliation_strings":["IPHS, University of Liverpool, Liverpool, Merseyside UK","IPHS, University of Liverpool, Liverpool, Merseyside UK#TAB#"],"affiliations":[{"raw_affiliation_string":"IPHS, University of Liverpool, Liverpool, Merseyside UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"IPHS, University of Liverpool, Liverpool, Merseyside UK#TAB#","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043179000"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.1948,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.90608044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9776999950408936,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9747999906539917,"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":0.7975215315818787},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7350185513496399},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7302278280258179},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6718240976333618},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5679517984390259},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5598200559616089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.527105450630188},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5167090892791748},{"id":"https://openalex.org/keywords/commodity","display_name":"Commodity","score":0.4414660632610321},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.438801646232605},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41171038150787354},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41012051701545715},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13473719358444214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07227027416229248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975215315818787},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7350185513496399},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7302278280258179},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6718240976333618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5679517984390259},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5598200559616089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.527105450630188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5167090892791748},{"id":"https://openalex.org/C2779439359","wikidata":"https://www.wikidata.org/wiki/Q317088","display_name":"Commodity","level":2,"score":0.4414660632610321},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.438801646232605},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41171038150787354},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41012051701545715},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13473719358444214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07227027416229248},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2595188.2595214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d7b78484-c8ae-44bc-9a43-01e53895cadc","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/d7b78484-c8ae-44bc-9a43-01e53895cadc","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19608173/Alex_and_Burns_2014_Estimating_and_rating_the_quality.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/d7b78484-c8ae-44bc-9a43-01e53895cadc","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/d7b78484-c8ae-44bc-9a43-01e53895cadc","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19608173/Alex_and_Burns_2014_Estimating_and_rating_the_quality.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320309","display_name":"Joint Information Systems Committee","ror":"https://ror.org/01rv9gx86"},{"id":"https://openalex.org/F4320334609","display_name":"Arts and Humanities Research Council","ror":"https://ror.org/0505m1554"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2101793424.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W205797039","https://openalex.org/W1699166917","https://openalex.org/W1952602359","https://openalex.org/W2003094793","https://openalex.org/W2009102799","https://openalex.org/W2011067322","https://openalex.org/W2015991179","https://openalex.org/W2037789405","https://openalex.org/W2133058591","https://openalex.org/W2155381731"],"related_works":["https://openalex.org/W4234903612","https://openalex.org/W4249539542","https://openalex.org/W2357241418","https://openalex.org/W2565085024","https://openalex.org/W2789919619","https://openalex.org/W4238075012","https://openalex.org/W2086064646","https://openalex.org/W2353015320","https://openalex.org/W2119135658","https://openalex.org/W2728450881"],"abstract_inverted_index":{"The":[0],"focus":[1],"of":[2,9,43,52,61,81,108,142,148],"this":[3],"paper":[4],"is":[5],"on":[6,31,137],"the":[7,26,106,131,146],"quality":[8,80,99,111],"historical":[10,48,143],"text":[11,22,49,79,83,98,138],"digitised":[12],"through":[13],"optical":[14],"character":[15],"recognition":[16,34],"(OCR)":[17],"and":[18,36,56,59,66,84,140],"how":[19,86,96],"it":[20],"affects":[21],"mining.":[23],"We":[24,72,93],"study":[25,147],"effect":[27],"OCR":[28,70],"errors":[29],"have":[30],"named":[32],"entity":[33],"(NER)":[35],"show":[37],"that":[38],"in":[39],"a":[40,74,110],"random":[41],"sample":[42],"documents":[44,115,144],"picked":[45],"from":[46],"several":[47],"collections,":[50],"30.6%":[51],"false":[53],"negative":[54],"commodity":[55,65],"location":[57,67],"mentions":[58,68],"13.3%":[60],"all":[62],"manually":[63],"annotated":[64],"contain":[69],"errors.":[71],"introduce":[73],"simple":[75],"method":[76],"for":[77,145],"estimating":[78],"OCRed":[82],"examine":[85],"well":[87],"human":[88],"raters":[89],"can":[90],"evaluate":[91],"it.":[92],"also":[94],"illustrate":[95],"automatic":[97],"estimation":[100],"compares":[101],"to":[102],"manual":[103],"rating":[104],"with":[105],"aim":[107],"determining":[109],"threshold":[112],"below":[113],"which":[114,135],"could":[116],"potentially":[117],"be":[118],"discarded":[119],"or":[120],"would":[121],"require":[122],"extensive":[123],"correction":[124],"first.":[125],"This":[126],"work":[127],"was":[128],"conducted":[129],"during":[130],"Trading":[132],"Consequences":[133],"project":[134],"focussed":[136],"mining":[139],"visualisation":[141],"nineteenth":[149],"century":[150],"trade.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
