{"id":"https://openalex.org/W2005898500","doi":"https://doi.org/10.1145/1255175.1255247","title":"A new generation of textual corpora","display_name":"A new generation of textual corpora","publication_year":2007,"publication_date":"2007-06-18","ids":{"openalex":"https://openalex.org/W2005898500","doi":"https://doi.org/10.1145/1255175.1255247","mag":"2005898500"},"language":"en","primary_location":{"id":"doi:10.1145/1255175.1255247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","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/A5005561151","display_name":"Gordon Stewart","orcid":"https://orcid.org/0000-0003-0244-2980"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Stewart","raw_affiliation_strings":["Harvard University, Cambridge, MA","Harvard University, Cambridge, Ma.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, Ma.#TAB#","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112237032","display_name":"Gregory Crane","orcid":"https://orcid.org/0000-0001-6847-2811"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Crane","raw_affiliation_strings":["Tufts University, Medford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066134932","display_name":"Alison Babeu","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alison Babeu","raw_affiliation_strings":["Tufts University, Medford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.5026,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98676081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9954000115394592,"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":0.9951000213623047,"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":0.7261052131652832},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.5898716449737549},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5624473690986633},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5406621694564819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5233967900276184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463919699192047},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.414293110370636},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3624882102012634},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.20405876636505127},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1392923891544342},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11326032876968384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261052131652832},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5898716449737549},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5624473690986633},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5406621694564819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5233967900276184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463919699192047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.414293110370636},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3624882102012634},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.20405876636505127},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1392923891544342},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11326032876968384},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1255175.1255247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W63741873","https://openalex.org/W114568238","https://openalex.org/W354027070","https://openalex.org/W1512888954","https://openalex.org/W1524610104","https://openalex.org/W1531901927","https://openalex.org/W1577737098","https://openalex.org/W1594556796","https://openalex.org/W1892839881","https://openalex.org/W1906503946","https://openalex.org/W1924623951","https://openalex.org/W1937243607","https://openalex.org/W1952210680","https://openalex.org/W1965753998","https://openalex.org/W1967197336","https://openalex.org/W1979773350","https://openalex.org/W1982012519","https://openalex.org/W2014007504","https://openalex.org/W2019520758","https://openalex.org/W2031185992","https://openalex.org/W2052918223","https://openalex.org/W2054770804","https://openalex.org/W2056970273","https://openalex.org/W2057960659","https://openalex.org/W2061235289","https://openalex.org/W2062518509","https://openalex.org/W2077419346","https://openalex.org/W2081699028","https://openalex.org/W2097358332","https://openalex.org/W2104543051","https://openalex.org/W2105981924","https://openalex.org/W2121015273","https://openalex.org/W2125055259","https://openalex.org/W2143307633","https://openalex.org/W2149551320","https://openalex.org/W2158171136","https://openalex.org/W2165254367","https://openalex.org/W2170295423","https://openalex.org/W2295218488","https://openalex.org/W2396438321","https://openalex.org/W2500014740","https://openalex.org/W2912044497","https://openalex.org/W2935885081","https://openalex.org/W3087927280","https://openalex.org/W4256238177"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W2756595502","https://openalex.org/W2010789764","https://openalex.org/W2187233292","https://openalex.org/W4389422031","https://openalex.org/W2219281195"],"abstract_inverted_index":{"While":[0],"digital":[1,127,158],"libraries":[2],"based":[3],"on":[4],"page":[5],"images":[6],"and":[7,26,42,83,177],"automatically":[8],"generated":[9],"text":[10,55,117],"have":[11,62,130,152],"made":[12],"possible":[13],"massive":[14],"projects":[15],"such":[16,39],"as":[17,40,74,76],"the":[18,48,106,123,146],"Million":[19],"Book":[20],"Library,":[21],"Open":[22],"Content":[23],"Alliance,":[24],"Google,":[25],"others,":[27],"humanists":[28],"still":[29],"depend":[30],"upon":[31,64,149],"textual":[32],"corpora":[33,128,148],"expensively":[34],"produced":[35,88],"with":[36],"labor-intensive":[37],"methods":[38],"double-keyboarding":[41],"manual":[43,66],"correction.":[44],"This":[45],"paper":[46],"reports":[47],"results":[49,119],"from":[50],"an":[51],"analysis":[52],"of":[53,78,174,182],"OCR-generated":[54,116],"for":[56,81,154],"classical":[57,85],"Greek":[58,86],"source":[59],"texts.":[60],"Classicists":[61],"depended":[63],"specialized":[65],"keyboarding":[67,77],"that":[68,94,126],"costs":[69],"two":[70],"or":[71],"more":[72],"times":[73],"much":[75],"English":[79],"both":[80],"accuracy":[82,111],"because":[84],"OCR":[87,100],"no":[89],"usable":[90],"results.":[91],"We":[92],"found":[93],"we":[95,137,161],"could":[96],"produce":[97],"texts":[98],"by":[99,121],"that,":[101,120],"in":[102],"some":[103],"cases,":[104,115],"approached":[105],"99.95%":[107],"professional":[108],"data":[109],"entry":[110],"rate.":[112],"In":[113],"most":[114],"yielded":[118],"including":[122],"variant":[124],"readings":[125],"traditionally":[129],"left":[131],"out,":[132],"provide":[133,178],"better":[134,140],"recall":[135],"and,":[136],"argue,":[138],"can":[139],"serve":[141],"many":[142],"scholarly":[143],"needs":[144],"than":[145],"expensive":[147],"which":[150],"classicists":[151],"relied":[153],"a":[155,179],"generation.":[156],"As":[157],"collections":[159],"expand,":[160],"will":[162],"be":[163],"able":[164],"to":[165],"collate":[166],"multiple":[167],"editions":[168],"against":[169],"each":[170],"other,":[171],"identify":[172],"quotations":[173],"primary":[175],"sources,":[176],"new":[180],"generation":[181],"services.":[183]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
