{"id":"https://openalex.org/W1983926369","doi":"https://doi.org/10.1145/1568296.1568309","title":"Enabling information retrieval on historical document collections","display_name":"Enabling information retrieval on historical document collections","publication_year":2009,"publication_date":"2009-07-23","ids":{"openalex":"https://openalex.org/W1983926369","doi":"https://doi.org/10.1145/1568296.1568309","mag":"1983926369"},"language":"en","primary_location":{"id":"doi:10.1145/1568296.1568309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3438101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052161697","display_name":"Annette Gotscharek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127848","display_name":"Institut f\u00fcr Urheber- und Medienrecht","ror":"https://ror.org/035pp4s04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127848"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Annette Gotscharek","raw_affiliation_strings":["University of Munich"],"affiliations":[{"raw_affiliation_string":"University of Munich","institution_ids":["https://openalex.org/I4210127848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101909291","display_name":"Andreas Neumann","orcid":"https://orcid.org/0000-0002-7404-9793"},"institutions":[{"id":"https://openalex.org/I4210138660","display_name":"Bavarian State Library","ror":"https://ror.org/031h71w90","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210138660"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Neumann","raw_affiliation_strings":["Bavarian State Library"],"affiliations":[{"raw_affiliation_string":"Bavarian State Library","institution_ids":["https://openalex.org/I4210138660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013959345","display_name":"Ulrich Reffle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127848","display_name":"Institut f\u00fcr Urheber- und Medienrecht","ror":"https://ror.org/035pp4s04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127848"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Reffle","raw_affiliation_strings":["University of Munich"],"affiliations":[{"raw_affiliation_string":"University of Munich","institution_ids":["https://openalex.org/I4210127848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110248832","display_name":"Christoph Ringlstetter","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127848","display_name":"Institut f\u00fcr Urheber- und Medienrecht","ror":"https://ror.org/035pp4s04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127848"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Ringlstetter","raw_affiliation_strings":["University of Munich"],"affiliations":[{"raw_affiliation_string":"University of Munich","institution_ids":["https://openalex.org/I4210127848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109699155","display_name":"Klaus U. Schulz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127848","display_name":"Institut f\u00fcr Urheber- und Medienrecht","ror":"https://ror.org/035pp4s04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127848"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus U. Schulz","raw_affiliation_strings":["University of Munich"],"affiliations":[{"raw_affiliation_string":"University of Munich","institution_ids":["https://openalex.org/I4210127848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052161697"],"corresponding_institution_ids":["https://openalex.org/I4210127848"],"apc_list":null,"apc_paid":null,"fwci":10.9044,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.98417764,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7795738577842712},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6864891052246094},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6314727067947388},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.628210723400116},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5907692909240723},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5528874397277832},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5522782206535339},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5421186089515686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5270564556121826},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4400036931037903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41367143392562866},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1917933225631714},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15952584147453308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795738577842712},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6864891052246094},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6314727067947388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.628210723400116},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5907692909240723},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5528874397277832},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5522782206535339},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5421186089515686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5270564556121826},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4400036931037903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41367143392562866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1917933225631714},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15952584147453308},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1568296.1568309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:3438101","is_oa":true,"landing_page_url":"https://zenodo.org/record/3438101","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3438101","is_oa":true,"landing_page_url":"https://zenodo.org/record/3438101","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32953792","https://openalex.org/W105720630","https://openalex.org/W205797039","https://openalex.org/W860710217","https://openalex.org/W1555414055","https://openalex.org/W1581712682","https://openalex.org/W1882181510","https://openalex.org/W1974533997","https://openalex.org/W2011067322","https://openalex.org/W2021795960","https://openalex.org/W2063420976","https://openalex.org/W2090123457","https://openalex.org/W2096601602","https://openalex.org/W2137416755","https://openalex.org/W2149179161","https://openalex.org/W2187123015","https://openalex.org/W3023072958","https://openalex.org/W6673163408","https://openalex.org/W7038461238"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Due":[0],"to":[1,19,29,41,74,103,147,153,167,217],"the":[2,50,53,55,79,83,88,101,135,139,175,198],"large":[3],"number":[4],"of":[5,14,57,82,90,106,138,177,197],"spelling":[6],"variants":[7,47],"found":[8,48],"in":[9,38,49,122,134,180,220],"historical":[10,24,46,66,118,151,158,211],"texts,":[11],"standard":[12],"methods":[13],"Information":[15],"Retrieval":[16],"(IR)":[17],"fail":[18],"produce":[20],"satisfactory":[21,155],"results":[22,205],"on":[23,127,150],"document":[25],"collections.":[26],"In":[27,52,78],"order":[28],"improve":[30],"recall":[31,196],"for":[32,65,201,208],"search":[33],"engines,":[34],"modern":[35],"words":[36],"used":[37],"queries":[39],"have":[40,68],"be":[42],"associated":[43],"with":[44],"corresponding":[45],"documents.":[51],"literature,":[54],"use":[56],"(1)":[58],"special":[59],"matching":[60,91,114,143,178,199,218],"procedures":[61,92,144,179,219],"and":[62,93,116,195],"(2)":[63],"lexica":[64,94,212],"language":[67,159],"been":[69],"suggested":[70],"as":[71],"two":[72],"ways":[73],"solve":[75],"this":[76],"problem.":[77],"first":[80],"part":[81,137],"paper":[84,140],"we":[85,192],"show":[86],"how":[87],"construction":[89],"may":[95],"benefit":[96],"from":[97,183],"each":[98,202],"other,":[99],"leading":[100],"way":[102,125],"a":[104,117,154],"combination":[105],"both":[107],"approaches.":[108],"A":[109,130],"tool":[110],"is":[111,141,164,186],"presented":[112],"where":[113,174],"rules":[115],"lexicon":[119],"are":[120],"built":[121],"an":[123,169,214],"interleaved":[124],"based":[126],"corpus":[128],"analysis.":[129],"crucial":[131],"question":[132],"considered":[133],"second":[136],"if":[142],"alone":[145],"suffice":[146],"lift":[148],"IR":[149,221],"texts":[152],"level.":[156],"Since":[157],"changes":[160],"over":[161],"centuries":[162,185],"it":[163],"not":[165],"simple":[166],"obtain":[168],"answer.":[170],"We":[171],"present":[172],"experiments":[173],"performance":[176],"text":[181],"collections":[182],"four":[184],"studied.":[187],"After":[188],"classifying":[189],"missed":[190],"vocabulary,":[191],"measure":[193],"precision":[194],"procedure":[200],"period.":[203],"Our":[204],"indicate":[206],"that":[207],"earlier":[209],"periods":[210],"represent":[213],"important":[215],"corrective":[216],"applications.":[222]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}