{"id":"https://openalex.org/W2982261395","doi":"https://doi.org/10.1145/3322905.3322910","title":"Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification","display_name":"Automatic Semantic Text Tagging on Historical Lexica by Combining OCR and Typography Classification","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2982261395","doi":"https://doi.org/10.1145/3322905.3322910","mag":"2982261395"},"language":"en","primary_location":{"id":"doi:10.1145/3322905.3322910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3322905.3322910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3322905.3322910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3322905.3322910","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063938010","display_name":"Christian Reul","orcid":"https://orcid.org/0000-0002-1776-1469"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Reul","raw_affiliation_strings":["Centre for Philology and Digitality, University of W\u00fcrzburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Philology and Digitality, University of W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042834788","display_name":"Sebastian G\u00f6ttel","orcid":null},"institutions":[{"id":"https://openalex.org/I23277345","display_name":"Berlin-Brandenburg Academy of Sciences and Humanities","ror":"https://ror.org/05jgq9443","country_code":"DE","type":"education","lineage":["https://openalex.org/I23277345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian G\u00f6ttel","raw_affiliation_strings":["Berlin-Brandenburg Academy of Sciences and Humanities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin-Brandenburg Academy of Sciences and Humanities","institution_ids":["https://openalex.org/I23277345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086884211","display_name":"Uwe Springmann","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uwe Springmann","raw_affiliation_strings":["Center for Information and Language Processing; LMU Munich","LMU Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing; LMU Munich","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"LMU Munich","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014007811","display_name":"Christoph Wick","orcid":"https://orcid.org/0000-0003-3958-6240"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Wick","raw_affiliation_strings":["Chair for Artificial Intelligence, University of W\u00fcrzburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair for Artificial Intelligence, University of W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032523664","display_name":"Kay-Michael W\u00fcrzner","orcid":null},"institutions":[{"id":"https://openalex.org/I23277345","display_name":"Berlin-Brandenburg Academy of Sciences and Humanities","ror":"https://ror.org/05jgq9443","country_code":"DE","type":"education","lineage":["https://openalex.org/I23277345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kay-Michael W\u00fcrzner","raw_affiliation_strings":["Berlin-Brandenburg Academy of Sciences and Humanities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin-Brandenburg Academy of Sciences and Humanities","institution_ids":["https://openalex.org/I23277345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043517672","display_name":"Frank Puppe","orcid":"https://orcid.org/0000-0002-7106-3223"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Puppe","raw_affiliation_strings":["Chair for Artificial Intelligence, University of W\u00fcrzburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair for Artificial Intelligence, University of W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4068,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66353315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9907000064849854,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9812999963760376,"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/typography","display_name":"Typography","score":0.9482610821723938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787162721157074},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6552817225456238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802626013755798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5694631338119507},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4783363342285156},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.47003787755966187},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4594070017337799},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3420732021331787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2828790545463562},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23138585686683655},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09150034189224243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07288527488708496}],"concepts":[{"id":"https://openalex.org/C166422571","wikidata":"https://www.wikidata.org/wiki/Q159964","display_name":"Typography","level":2,"score":0.9482610821723938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787162721157074},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6552817225456238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802626013755798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5694631338119507},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4783363342285156},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.47003787755966187},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4594070017337799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3420732021331787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2828790545463562},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23138585686683655},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09150034189224243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07288527488708496},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3322905.3322910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3322905.3322910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3322905.3322910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:1451482","is_oa":true,"landing_page_url":"https://zenodo.org/record/1451482","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePoster"},{"id":"doi:10.5281/zenodo.1451482","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1451482","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3322905.3322910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3322905.3322910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3322905.3322910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982261395.pdf","grobid_xml":"https://content.openalex.org/works/W2982261395.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2028587221","https://openalex.org/W2077221566","https://openalex.org/W2097607613","https://openalex.org/W2113463266","https://openalex.org/W2113723031","https://openalex.org/W2122145500","https://openalex.org/W2597920441","https://openalex.org/W2789003796","https://openalex.org/W2917178326","https://openalex.org/W2964057904","https://openalex.org/W3013597222"],"related_works":["https://openalex.org/W2320296373","https://openalex.org/W2147687867","https://openalex.org/W2582695981","https://openalex.org/W2496907786","https://openalex.org/W3135049875","https://openalex.org/W2483185727","https://openalex.org/W2612325988","https://openalex.org/W1535446683","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":{"When":[0],"converting":[1],"historical":[2,150],"lexica":[3],"into":[4],"electronic":[5],"form":[6],"the":[7,20,37,72,77,97,110,128,136],"goal":[8],"is":[9],"not":[10],"only":[11],"to":[12,24,35,70,76,131,133,140],"obtain":[13],"a":[14,26,45,49,83,88,102,116,123],"high":[15],"quality":[16],"OCR":[17,58,63,78],"result":[18],"for":[19],"text":[21,80],"but":[22],"also":[23],"perform":[25],"precise":[27],"automatic":[28],"recognition":[29,66,125],"of":[30,107,135],"typographical":[31],"attributes":[32],"in":[33],"order":[34],"capture":[36],"logical":[38],"structure.":[39],"For":[40],"that":[41,47,126],"purpose,":[42],"we":[43,86,114],"present":[44],"method":[46],"enables":[48],"fine-grained":[50],"typography":[51,65,74,124,157],"classification":[52],"by":[53],"training":[54],"an":[55],"open":[56],"source":[57],"engine":[59],"both":[60],"on":[61],"traditional":[62],"and":[64,67,122,152],"show":[68],"how":[69],"map":[71],"obtained":[73],"information":[75],"recognized":[79],"output.":[81],"As":[82],"test":[84],"case,":[85],"used":[87],"German":[89],"dictionary":[90],"(Sander's":[91],"W\u00f6rterbuch":[92],"der":[93],"Deutschen":[94],"Sprache)":[95],"from":[96],"19th":[98],"century,":[99],"which":[100],"comprises":[101],"particularly":[103],"complex":[104],"semantic":[105],"function":[106],"typography.":[108],"Despite":[109],"very":[111],"challenging":[112],"material,":[113],"achieved":[115],"character":[117],"error":[118],"rate":[119],"below":[120],"0.4%":[121],"assigns":[127],"correct":[129],"label":[130],"close":[132],"99%":[134],"words.":[137],"In":[138],"contrast":[139],"many":[141],"existing":[142],"methods,":[143],"our":[144],"novel":[145],"approach":[146],"works":[147],"with":[148,155],"real":[149],"data":[151],"can":[153],"deal":[154],"frequent":[156],"changes":[158],"even":[159],"within":[160],"lines.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
