{"id":"https://openalex.org/W2048135704","doi":"https://doi.org/10.1145/1141753.1141835","title":"Automatic extraction of table metadata from digital documents","display_name":"Automatic extraction of table metadata from digital documents","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2048135704","doi":"https://doi.org/10.1145/1141753.1141835","mag":"2048135704"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","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/A5045056058","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-4274-5313"},"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":"Ying Liu","raw_affiliation_strings":["Pennsylvania State University, University Park, Pennsylvania","College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"College of Information Science and Technology, Pennsylvania State University, University Park, PA#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":"Prasenjit Mitra","raw_affiliation_strings":["Pennsylvania State University, University Park, Pennsylvania","College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","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. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, Pennsylvania","College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","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":"Kun Bai","raw_affiliation_strings":["Pennsylvania State University, University Park, Pennsylvania","College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, Pennsylvania","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"College of Information Science and Technology, Pennsylvania State University, University Park, PA#TAB#","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":3.0357,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91074898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"339","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9932000041007996,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9930999875068665,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9417426586151123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8562523722648621},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7836070656776428},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7180743217468262},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.6965238451957703},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6694015264511108},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.5559049844741821},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.5389988422393799},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5252953171730042},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4998633861541748},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.48384466767311096},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.47509872913360596},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.45718973875045776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35634124279022217},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3379747271537781}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9417426586151123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8562523722648621},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7836070656776428},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7180743217468262},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.6965238451957703},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6694015264511108},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.5559049844741821},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.5389988422393799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5252953171730042},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4998633861541748},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.48384466767311096},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.47509872913360596},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.45718973875045776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35634124279022217},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3379747271537781},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"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/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1141753.1141835","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.9713","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.9713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://chemxseer.ist.psu.edu/about/digital_library/jcdl2006-liu.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.1489","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.1489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/faculty/p/u/pum10/jcdl06-table.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2034797903","https://openalex.org/W2163534337","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2374379029","https://openalex.org/W3016521766","https://openalex.org/W2183628870","https://openalex.org/W2379265733","https://openalex.org/W92613187","https://openalex.org/W3084772717","https://openalex.org/W1503116306","https://openalex.org/W2360250168","https://openalex.org/W132275995","https://openalex.org/W2388609536"],"abstract_inverted_index":{"Tables":[0],"are":[1,17,53],"used":[2,19],"to":[3,20,56,90],"present,":[4],"list,":[5],"summarize,":[6],"and":[7,26,35,45,49,62,96,104,115],"structure":[8,48],"important":[9,55],"data":[10,25,43],"in":[11],"documents.":[12,119],"In":[13,38,79],"scholarly":[14],"articles,":[15],"they":[16],"often":[18],"present":[21],"the":[22,47,65,75,92,100],"relationships":[23],"among":[24],"high-light":[27],"a":[28,84],"collection":[29],"of":[30,51,67,77,86,102],"results":[31],"obtained":[32],"from":[33],"experiments":[34],"scientific":[36],"analysis.":[37],"digital":[39],"libraries,":[40],"extracting":[41],"this":[42,80],"automatically":[44],"understanding":[46],"content":[50],"tables":[52,68,103],"very":[54],"many":[57],"applications.":[58],"Automatic":[59],"identification":[60],"extraction,":[61],"search":[63],"for":[64],"contents":[66,101],"can":[69],"be":[70],"made":[71],"more":[72],"precise":[73],"with":[74],"help":[76],"metadata.":[78],"paper,":[81],"we":[82],"propose":[83],"set":[85],"medium-independent":[87],"table":[88,93,109],"metadata":[89,110],"facilitate":[91],"indexing,":[94],"searching,":[95],"exchanging.":[97],"To":[98],"extract":[99],"their":[105],"metadata,":[106],"an":[107],"automatic":[108],"extraction":[111],"algorithm":[112],"is":[113],"designed":[114],"tested":[116],"on":[117],"PDF":[118]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
