{"id":"https://openalex.org/W2059395655","doi":"https://doi.org/10.1145/2595188.2595206","title":"Automated assignment of topics to OCRed historical texts","display_name":"Automated assignment of topics to OCRed historical texts","publication_year":2014,"publication_date":"2014-05-19","ids":{"openalex":"https://openalex.org/W2059395655","doi":"https://doi.org/10.1145/2595188.2595206","mag":"2059395655"},"language":"en","primary_location":{"id":"doi:10.1145/2595188.2595206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595206","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":"conference-paper","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/A5001867012","display_name":"Florian Fink","orcid":null},"institutions":[{"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":"Florian Fink","raw_affiliation_strings":["CIS, University of Munich","CIS -- University of Munich#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIS, University of Munich","institution_ids":[]},{"raw_affiliation_string":"CIS -- University of Munich#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110248832","display_name":"Christoph Ringlstetter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Ringlstetter","raw_affiliation_strings":["Gini"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gini","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109699155","display_name":"Klaus U. Schulz","orcid":null},"institutions":[{"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":"Klaus Schulz","raw_affiliation_strings":["CIS, University of Munich","CIS -- University of Munich#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIS, University of Munich","institution_ids":[]},{"raw_affiliation_string":"CIS -- University of Munich#TAB#","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12292877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9939000010490417,"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/orthography","display_name":"Orthography","score":0.9551175236701965},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8135578632354736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028533458709717},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6573397517204285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5909756422042847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5436527132987976},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5242058038711548},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5153374075889587},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.48137739300727844},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47004929184913635},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4527944326400757},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3854605257511139},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3747377395629883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26091858744621277},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.0822991132736206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06608396768569946}],"concepts":[{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.9551175236701965},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8135578632354736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028533458709717},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6573397517204285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5909756422042847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436527132987976},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5242058038711548},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5153374075889587},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.48137739300727844},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47004929184913635},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4527944326400757},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3854605257511139},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3747377395629883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26091858744621277},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0822991132736206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06608396768569946},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2595188.2595206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595206","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W159230833","https://openalex.org/W1880262756","https://openalex.org/W1978841319","https://openalex.org/W2041711198","https://openalex.org/W2042980227","https://openalex.org/W2063420976","https://openalex.org/W7047636377"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W2349956239","https://openalex.org/W611030372","https://openalex.org/W4389684388","https://openalex.org/W2729795264"],"abstract_inverted_index":{"During":[0],"the":[1,16,87,105,145,149],"last":[2],"decade,":[3],"a":[4,43,58,157,161],"huge":[5],"amount":[6],"of":[7,20,38,97,107],"OCRed":[8,74],"historical":[9,98,111],"texts":[10,75],"has":[11],"been":[12],"made":[13],"available":[14],"on":[15,52,113],"Internet.":[17],"For":[18],"most":[19],"these":[21,48],"documents":[22],"meta":[23],"data":[24],"are":[25,95],"missing":[26],"that":[27,135],"assign":[28],"topic":[29,63,114,137],"categories":[30],"from":[31,76,156],"library":[32],"classification":[33],"systems":[34],"to":[35,47,73,90,103,140],"texts.":[36,132],"Data":[37],"this":[39],"form":[40],"would":[41],"offer":[42],"much":[44],"better":[45],"access":[46],"collections.":[49],"We":[50,133],"report":[51],"an":[53,77],"experiment":[54,88],"where":[55],"we":[56,116],"used":[57,85],"completely":[59],"automated":[60,136],"system":[61],"for":[62,67,130,143],"assignment,":[64],"originally":[65],"designed":[66],"modern":[68],"texts,":[69],"and":[70,94,110,121,148],"apply":[71],"it":[72],"18th":[78],"century":[79],"German":[80],"lexicon":[81],"(Zedler).":[82],"Lexicon":[83],"pages/images":[84],"in":[86,122,160],"lead":[89],"poor":[91],"OCR":[92,108,146],"quality":[93],"full":[96],"spelling":[99],"variants.":[100],"In":[101],"order":[102],"measure":[104],"influence":[106],"errors":[109],"orthography":[112,129],"detection,":[115],"created":[117],"ground":[118,124,151],"truth":[119,125,152],"versions":[120,126],"addition":[123],"with":[127],"modernized":[128],"all":[131],"found":[134],"assignment":[138],"leads":[139],"useful":[141],"results":[142],"both":[144],"output":[147],"two":[150],"versions.":[153],"Difficulties":[154],"arise":[155],"\"changing":[158],"world\"":[159],"(e.g.,":[162],"technical)":[163],"field":[164],"as":[165,167],"well":[166],"language":[168],"changes":[169],"beyond":[170],"simple":[171],"orthography.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
