{"id":"https://openalex.org/W2021795960","doi":"https://doi.org/10.1109/icdar.2007.4377029","title":"Google Book Search: Document Understanding on a Massive Scale","display_name":"Google Book Search: Document Understanding on a Massive Scale","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2021795960","doi":"https://doi.org/10.1109/icdar.2007.4377029","mag":"2021795960"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377029","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","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/A5109000979","display_name":"Luc Vincent","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"L. Vincent","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google Mountain View#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109000979"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":19.0,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.8219000101089478,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"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/T12353","display_name":"Lexicography and Language Studies","score":0.8219000101089478,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6565367579460144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6495028734207153},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5607635974884033},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5587291121482849},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.52381831407547},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39905762672424316},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09276741743087769}],"concepts":[{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6565367579460144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495028734207153},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5607635974884033},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5587291121482849},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.52381831407547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39905762672424316},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09276741743087769},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdar.2007.4377029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377029","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.465.2901","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.2901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vincent-net.com/luc/papers/07icdar_googlebooks.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"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":9,"referenced_works":["https://openalex.org/W1663315404","https://openalex.org/W2001642682","https://openalex.org/W2082163619","https://openalex.org/W2096210305","https://openalex.org/W2162031011","https://openalex.org/W6637103125","https://openalex.org/W6650820226","https://openalex.org/W6671261282","https://openalex.org/W6674923383"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W380379685","https://openalex.org/W4213212078","https://openalex.org/W2062838854","https://openalex.org/W1536049545","https://openalex.org/W574531438","https://openalex.org/W2187227032","https://openalex.org/W2112788825","https://openalex.org/W3123265518","https://openalex.org/W1963735073"],"abstract_inverted_index":{"Unveiled":[0],"in":[1,38],"late":[2],"2004,":[3],"Google":[4,50],"Book":[5],"Search":[6],"is":[7,51],"an":[8],"ambitious":[9],"program":[10],"to":[11,59],"make":[12],"all":[13],"the":[14,23,47,54,62,65],"world's":[15],"books":[16],"discoverable":[17],"online.":[18],"The":[19],"sheer":[20],"scale":[21],"of":[22,28,46,64],"problem":[24],"brings":[25],"a":[26],"number":[27],"unique":[29],"document":[30,55],"analysis":[31,56],"and":[32],"understanding":[33],"challenges":[34],"that":[35,49],"are":[36],"outlined":[37],"this":[39],"paper.":[40],"We":[41],"also":[42],"go":[43],"over":[44],"some":[45],"ways":[48],"working":[52],"with":[53],"research":[57],"community":[58],"help":[60],"push":[61],"state":[63],"art.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}