{"id":"https://openalex.org/W1972311814","doi":"https://doi.org/10.1109/icdar.2007.4377052","title":"Searching for Tables in Digital Documents","display_name":"Searching for Tables in Digital Documents","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W1972311814","doi":"https://doi.org/10.1109/icdar.2007.4377052","mag":"1972311814"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377052","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/A5100414092","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0001-9319-5940"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Y. Liu","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Pennsylvania State University, University Park#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University, University Park#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072519705","display_name":"Kun Bai","orcid":"https://orcid.org/0009-0008-8005-7424"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Bai","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Pennsylvania State University, University Park#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University, University Park#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Mitra","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Pennsylvania State University, University Park#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University, University Park#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Giles","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","Pennsylvania State University, University Park#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University, University Park#TAB#","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100414092"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.3806,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.55291723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9958000183105469,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9958000183105469,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9930999875068665,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8299450278282166},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8231263160705566},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6975735425949097},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6764721274375916},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6710879802703857},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6298946738243103},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5681787729263306},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42432278394699097},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.42266497015953064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4189910292625427},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3326111435890198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299450278282166},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8231263160705566},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6975735425949097},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6764721274375916},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6710879802703857},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6298946738243103},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5681787729263306},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42432278394699097},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.42266497015953064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4189910292625427},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3326111435890198},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4377052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377052","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1569639771","https://openalex.org/W1967830139","https://openalex.org/W1978394996","https://openalex.org/W1988217119","https://openalex.org/W2048135704","https://openalex.org/W2096782419","https://openalex.org/W2105693220","https://openalex.org/W2119476919","https://openalex.org/W4235592330"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2367099342"],"abstract_inverted_index":{"Tables":[0],"are":[1,7],"ubiquitous.":[2],"In":[3,34],"scientific":[4,50],"documents,":[5,51,59],"tables":[6,57,79],"widely":[8],"used":[9],"to":[10,29,65],"present":[11],"experimental":[12],"results":[13,88,97],"or":[14],"statistical":[15],"data":[16],"in":[17],"a":[18,82],"condensed":[19],"fashion.":[20],"Current":[21],"search":[22,30,45,66,103],"engines":[23],"do":[24],"not":[25],"allow":[26],"the":[27,86,110],"end-user":[28,111],"for":[31,67,78,113],"relevant":[32],"tables.":[33,68,114],"this":[35],"paper,":[36],"we":[37],"describe":[38],"TableSeer,":[39],"an":[40,72,90],"automatic":[41],"table":[42],"extraction":[43],"and":[44,62],"engine":[46],"system.":[47],"TableSeer":[48,84,100],"crawls":[49],"identifies":[52],"documents":[53],"with":[54],"tables,":[55],"extracts":[56],"from":[58],"indexes":[60],"them":[61],"enables":[63],"end-users":[64],"We":[69],"also":[70],"propose":[71],"extensive":[73],"set":[74],"of":[75],"medium-independent":[76],"metadata":[77],"representation.":[80],"Given":[81],"query,":[83],"ranks":[85],"returned":[87],"using":[89],"innovative":[91],"ranking":[92],"algorithm":[93],"-":[94],"TableRank.":[95],"Our":[96],"show":[98],"that":[99],"outperforms":[101],"popular":[102],"engines,":[104],"such":[105],"as":[106],"Google":[107],"Scholar":[108],"when":[109],"seeks":[112]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
