{"id":"https://openalex.org/W2014872868","doi":"https://doi.org/10.1145/1600193.1600236","title":"On lexical resources for digitization of historical documents","display_name":"On lexical resources for digitization of historical documents","publication_year":2009,"publication_date":"2009-09-16","ids":{"openalex":"https://openalex.org/W2014872868","doi":"https://doi.org/10.1145/1600193.1600236","mag":"2014872868"},"language":"en","primary_location":{"id":"doi:10.1145/1600193.1600236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600236","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052161697","display_name":"Annette Gotscharek","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":"Annette Gotscharek","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013959345","display_name":"Ulrich Reffle","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":"Ulrich Reffle","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110248832","display_name":"Christoph Ringlstetter","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":"Christoph Ringlstetter","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"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 U. Schulz","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":2.6808,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90859757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9934999942779541,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8287184238433838},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.789099931716919},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6568792462348938},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5548369884490967},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5476410388946533},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5406917929649353},{"id":"https://openalex.org/keywords/lexical-database","display_name":"Lexical database","score":0.5157907009124756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49073994159698486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48811373114585876},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4548240005970001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41035401821136475},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3277912139892578},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2619158625602722},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.14595666527748108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287184238433838},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.789099931716919},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6568792462348938},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5548369884490967},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5476410388946533},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5406917929649353},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.5157907009124756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49073994159698486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48811373114585876},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4548240005970001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41035401821136475},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3277912139892578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2619158625602722},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.14595666527748108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1600193.1600236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600236","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W105720630","https://openalex.org/W860710217","https://openalex.org/W1512858517","https://openalex.org/W1555414055","https://openalex.org/W1581712682","https://openalex.org/W1882181510","https://openalex.org/W1974533997","https://openalex.org/W2010595692","https://openalex.org/W2052227241","https://openalex.org/W2063420976","https://openalex.org/W2071003614","https://openalex.org/W2096601602","https://openalex.org/W2137416755","https://openalex.org/W2149179161","https://openalex.org/W7038461238"],"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/W2592115649","https://openalex.org/W4322582183","https://openalex.org/W1937392525","https://openalex.org/W2347632764"],"abstract_inverted_index":{"Many":[0],"European":[1],"libraries":[2],"are":[3,34,103,107,133],"currently":[4,44],"engaged":[5],"in":[6,20,82,142],"mass":[7],"digitization":[8],"projects":[9],"that":[10,205],"aim":[11],"to":[12,36,48,72,173,227],"make":[13],"historical":[14,41,59,83,116,168],"documents":[15,84,117,145,169],"and":[16,75,101,175,202,214,221],"corpora":[17],"online":[18],"available":[19],"the":[21,66,78,89,140,183,197],"Internet.":[22],"In":[23],"this":[24],"context,":[25],"appropriate":[26],"lexical":[27,113,127,224],"resources":[28,114,128,225],"play":[29],"a":[30,54,150,163],"double":[31],"role.":[32],"They":[33],"needed":[35],"improve":[37],"OCR":[38,56,200,220],"recognition":[39],"of":[40,77,91,152,179,192,216],"documents,":[42],"which":[43,154],"does":[45],"not":[46],"lead":[47,226],"satisfactory":[49],"results.":[50],"Second,":[51],"even":[52],"assuming":[53],"perfect":[55],"recognition,":[57],"since":[58,136],"language":[60],"differs":[61],"considerably":[62],"from":[63,170],"modern":[64],"language,":[65],"matching":[67],"process":[68],"between":[69],"queries":[70],"submitted":[71],"search":[73,79],"engines":[74],"variants":[76],"terms":[80],"found":[81],"needs":[85],"special":[86,92],"support.":[87],"While":[88],"usefulness":[90],"dictionaries":[93,213],"for":[94,115,189,199],"both":[95,219],"problems":[96],"seems":[97],"undisputed,":[98],"concrete":[99],"knowledge":[100],"experience":[102],"still":[104],"missing.":[105],"There":[106],"no":[108],"hints":[109],"about":[110],"what":[111],"optimal":[112],"should":[118],"look":[119],"like.":[120],"The":[121],"real":[122],"benefit":[123],"reached":[124,185],"by":[125],"optimized":[126],"is":[129],"unclear.":[130],"Both":[131],"questions":[132],"rather":[134],"complex":[135],"answers":[137],"depend":[138],"on":[139],"point":[141],"history":[143],"when":[144],"were":[146],"born.":[147],"We":[148,181],"present":[149,182],"series":[151],"experiments":[153,195],"illuminate":[155,196],"these":[156],"points.":[157],"For":[158,218],"our":[159,223],"evaluations":[160],"we":[161],"collected":[162],"large":[164],"corpus":[165],"covering":[166],"German":[167],"before":[171],"1500":[172],"1950":[174],"constructed":[176],"various":[177],"types":[178],"dictionaries.":[180],"coverage":[184],"with":[186],"each":[187],"dictionary":[188],"ten":[190],"subperiods":[191],"time.":[193,217],"Additional":[194],"improvements":[198],"accuracy":[201],"Information":[203],"Retrieval":[204],"can":[206],"be":[207],"reached,":[208],"again":[209],"looking":[210],"at":[211],"distinct":[212],"periods":[215],"IR,":[222],"substantial":[228],"improvements.":[229]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
