{"id":"https://openalex.org/W2111331041","doi":"https://doi.org/10.1145/2484762.2484796","title":"Using Lucene to index and search the digitized 1940 US census","display_name":"Using Lucene to index and search the digitized 1940 US census","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W2111331041","doi":"https://doi.org/10.1145/2484762.2484796","mag":"2111331041"},"language":"en","primary_location":{"id":"doi:10.1145/2484762.2484796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","raw_type":"proceedings-article"},"type":"article","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/A5089546440","display_name":"Liana Diesendruck","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liana Diesendruck","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025183449","display_name":"Rob Kooper","orcid":"https://orcid.org/0000-0002-5781-7287"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Kooper","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034386740","display_name":"Luigi Marini","orcid":"https://orcid.org/0000-0002-8511-0211"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luigi Marini","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059328010","display_name":"Kenton McHenry","orcid":"https://orcid.org/0000-0003-0367-2550"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenton McHenry","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089546440"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.5443,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72035242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983000159263611,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983000159263611,"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/T11106","display_name":"Data Management and Algorithms","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8466454744338989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8439197540283203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7281702756881714},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6796450614929199},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.6782033443450928},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5628073215484619},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5234332084655762},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5189414024353027},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5150513648986816},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.4936410188674927},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.48117026686668396},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.44991135597229004},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43003493547439575},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.422607958316803},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28673475980758667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2652556896209717}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8466454744338989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439197540283203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7281702756881714},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6796450614929199},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.6782033443450928},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5628073215484619},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5234332084655762},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5189414024353027},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5150513648986816},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.4936410188674927},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.48117026686668396},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.44991135597229004},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43003493547439575},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.422607958316803},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28673475980758667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2652556896209717},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484762.2484796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1910218551","display_name":null,"funder_award_id":"NSF OCI 05-25308, OCI 05-04064, OCI-1053575","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306128","display_name":"National Archives and Records Administration","ror":"https://ror.org/032214n64"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1542934258","https://openalex.org/W1932188282","https://openalex.org/W2000782346","https://openalex.org/W2003553779","https://openalex.org/W2006504684","https://openalex.org/W2035890032","https://openalex.org/W2162838084","https://openalex.org/W2167929403","https://openalex.org/W4249507550"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"An":[0],"improved":[1],"approach":[2],"towards":[3],"enabling":[4],"search":[5],"capabilities":[6],"over":[7],"large":[8],"digitized":[9,38,141],"document":[10,142],"archives":[11],"is":[12,76,88],"described,":[13],"in":[14,20,51,132],"which":[15],"Lucene":[16,120],"indices":[17],"were":[18],"incorporated":[19],"a":[21,34,82],"framework":[22],"developed":[23],"to":[24,29,44,46,60,90,106,110,121],"provide":[25,107],"automatic":[26],"searchable":[27],"access":[28,109],"the":[30,48,52,68,91,99,111,135],"1940":[31],"US":[32],"Census,":[33],"collection":[35],"composed":[36],"of":[37,66,85,118,126,134,144],"handwritten":[39,49],"forms.":[40],"As":[41],"an":[42,79,101],"alternative":[43],"trying":[45],"recognize":[47],"text":[50],"images,":[53],"Word":[54],"Spotting":[55],"feature":[56,112],"vectors":[57,124],"are":[58,130],"used":[59],"describe":[61],"each":[62],"cell's":[63],"content.":[64],"Instead":[65],"querying":[67],"system":[69],"using":[70,119],"regular":[71],"ASCII":[72],"text,":[73],"any":[74],"query":[75],"rendered":[77],"as":[78],"image":[80],"and":[81,116],"ranked":[83],"list":[84],"matching":[86],"results":[87],"presented":[89],"user.":[92],"Among":[93],"other":[94,127],"pre-processing":[95],"steps":[96],"required":[97],"by":[98],"framework,":[100],"index":[102,122],"must":[103],"be":[104],"compiled":[105],"fast":[108],"vectors.":[113],"The":[114],"advantages":[115],"drawbacks":[117],"these":[123],"instead":[125],"indexing":[128],"methods":[129],"discussed":[131],"light":[133],"challenges":[136],"confronted":[137],"when":[138],"dealing":[139],"with":[140],"collections":[143],"considerable":[145],"size.":[146]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
