{"id":"https://openalex.org/W2028074077","doi":"https://doi.org/10.1145/1568296.1568304","title":"Text retrieval from early printed books","display_name":"Text retrieval from early printed books","publication_year":2009,"publication_date":"2009-07-23","ids":{"openalex":"https://openalex.org/W2028074077","doi":"https://doi.org/10.1145/1568296.1568304","mag":"2028074077"},"language":"en","primary_location":{"id":"doi:10.1145/1568296.1568304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568304","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":"http://hdl.handle.net/2158/373561","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011511343","display_name":"Simone Marinai","orcid":"https://orcid.org/0000-0002-6702-2277"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone Marinai","raw_affiliation_strings":["University of Firenze, Firenze, Italy"],"affiliations":[{"raw_affiliation_string":"University of Firenze, Firenze, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011511343"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.24976045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9947999715805054,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8210664987564087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916488647460938},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6801491975784302},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6326498985290527},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.605117678642273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5738852620124817},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5538620948791504},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5322907567024231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116291642189026},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4862009882926941},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09334853291511536},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.059745997190475464}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8210664987564087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916488647460938},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6801491975784302},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6326498985290527},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.605117678642273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5738852620124817},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5538620948791504},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5322907567024231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116291642189026},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4862009882926941},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09334853291511536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.059745997190475464},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1568296.1568304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568304","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:flore.unifi.it:2158/373561","is_oa":true,"landing_page_url":"http://hdl.handle.net/2158/373561","pdf_url":"http://hdl.handle.net/2158/373561","source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:flore.unifi.it:2158/373561","is_oa":true,"landing_page_url":"http://hdl.handle.net/2158/373561","pdf_url":"http://hdl.handle.net/2158/373561","source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2028074077.pdf","grobid_xml":"https://content.openalex.org/works/W2028074077.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1487560819","https://openalex.org/W1511397260","https://openalex.org/W1529012620","https://openalex.org/W1550565663","https://openalex.org/W1570195116","https://openalex.org/W1608397574","https://openalex.org/W1679913846","https://openalex.org/W1887599766","https://openalex.org/W1892839881","https://openalex.org/W1952936656","https://openalex.org/W1967238710","https://openalex.org/W1983926369","https://openalex.org/W1996226495","https://openalex.org/W2011067322","https://openalex.org/W2020509212","https://openalex.org/W2053406980","https://openalex.org/W2058931781","https://openalex.org/W2069172670","https://openalex.org/W2085780312","https://openalex.org/W2089119080","https://openalex.org/W2100630820","https://openalex.org/W2104309475","https://openalex.org/W2107950441","https://openalex.org/W2109645316","https://openalex.org/W2128318879","https://openalex.org/W2133058591","https://openalex.org/W2140217726","https://openalex.org/W2149470434","https://openalex.org/W2149507380","https://openalex.org/W2150988072","https://openalex.org/W2154495259","https://openalex.org/W2156301828","https://openalex.org/W2159800521","https://openalex.org/W2165152049","https://openalex.org/W2167929403","https://openalex.org/W2168868236","https://openalex.org/W2614290706","https://openalex.org/W4205749566","https://openalex.org/W4229571151","https://openalex.org/W4238410424"],"related_works":["https://openalex.org/W1991513203","https://openalex.org/W3178467699","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W1583770177","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2058548953","https://openalex.org/W2785359773"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2],"text":[3],"indexing":[4],"and":[5,15,32],"retrieval":[6],"technique":[7],"that":[8],"does":[9],"not":[10],"rely":[11],"on":[12,36],"word":[13],"segmentation":[14],"is":[16,25],"tolerant":[17],"to":[18,27],"errors":[19],"in":[20],"character":[21],"segmentation.":[22],"The":[23],"method":[24],"designed":[26],"process":[28],"early":[29],"printed":[30],"documents":[31],"we":[33],"evaluate":[34],"it":[35],"the":[37],"well":[38],"known":[39],"Latin":[40],"Gutenberg":[41],"Bible.":[42]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
