{"id":"https://openalex.org/W2518276024","doi":"https://doi.org/10.1145/2960811.2967152","title":"Configurable Table Structure Recognition in Untagged PDF documents","display_name":"Configurable Table Structure Recognition in Untagged PDF documents","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2518276024","doi":"https://doi.org/10.1145/2960811.2967152","mag":"2518276024"},"language":"en","primary_location":{"id":"doi:10.1145/2960811.2967152","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","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/A5041210817","display_name":"Alexey Shigarov","orcid":"https://orcid.org/0000-0001-5572-5349"},"institutions":[{"id":"https://openalex.org/I4210148533","display_name":"Institute for System Dynamics and Control Theory","ror":"https://ror.org/04wteqw51","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I1313323035","https://openalex.org/I4210127387","https://openalex.org/I4210148533","https://openalex.org/I4210164537"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexey Shigarov","raw_affiliation_strings":["Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed"],"affiliations":[{"raw_affiliation_string":"Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed","institution_ids":["https://openalex.org/I4210148533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017095385","display_name":"Andrey Mikhailov","orcid":"https://orcid.org/0000-0003-4057-4511"},"institutions":[{"id":"https://openalex.org/I4210148533","display_name":"Institute for System Dynamics and Control Theory","ror":"https://ror.org/04wteqw51","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I1313323035","https://openalex.org/I4210127387","https://openalex.org/I4210148533","https://openalex.org/I4210164537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Mikhailov","raw_affiliation_strings":["Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed"],"affiliations":[{"raw_affiliation_string":"Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed","institution_ids":["https://openalex.org/I4210148533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067488687","display_name":"Andrey Altaev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148533","display_name":"Institute for System Dynamics and Control Theory","ror":"https://ror.org/04wteqw51","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I1313323035","https://openalex.org/I4210127387","https://openalex.org/I4210148533","https://openalex.org/I4210164537"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Altaev","raw_affiliation_strings":["Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed"],"affiliations":[{"raw_affiliation_string":"Matrosov Institute for System Dynamics and Control Theory of SB RAS, Irkutsk, Russian Fed","institution_ids":["https://openalex.org/I4210148533"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041210817"],"corresponding_institution_ids":["https://openalex.org/I4210148533"],"apc_list":null,"apc_paid":null,"fwci":2.3652,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.92592105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9975000023841858,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8046794533729553},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7920506596565247},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7709743976593018},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6594340801239014},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5895605683326721},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.48012566566467285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38914114236831665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.334369957447052},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25446391105651855},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10478654503822327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046794533729553},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7920506596565247},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7709743976593018},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6594340801239014},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5895605683326721},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.48012566566467285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38914114236831665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.334369957447052},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25446391105651855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10478654503822327},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2960811.2967152","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G153344985","display_name":null,"funder_award_id":"15-37-20042, 14-07-00166","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"}],"funders":[{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W171350836","https://openalex.org/W1151363261","https://openalex.org/W1506666816","https://openalex.org/W2009659675","https://openalex.org/W2022351003","https://openalex.org/W2036596234","https://openalex.org/W2038264730","https://openalex.org/W2060507674","https://openalex.org/W2074966879","https://openalex.org/W2107092590","https://openalex.org/W2132083030","https://openalex.org/W2137998699","https://openalex.org/W2142809404","https://openalex.org/W2165382068","https://openalex.org/W4229847583"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2784269775","https://openalex.org/W2952904874","https://openalex.org/W324626582"],"abstract_inverted_index":{"Today,":[0],"PDF":[1,14,62],"is":[2,43,65],"one":[3],"of":[4,37,70,100],"the":[5,11,28,38,86,94],"most":[6],"popular":[7],"document":[8],"formats":[9],"in":[10,60],"web.":[12],"Many":[13],"documents":[15,42],"are":[16],"not":[17],"images,":[18],"but":[19],"remain":[20],"untagged.":[21],"They":[22],"have":[23],"no":[24],"tags":[25],"for":[26,56,76,85,98],"identifying":[27],"logical":[29],"reading":[30],"order,":[31],"paragraphs,":[32],"figures,":[33],"and":[34,73,88],"tables.":[35],"One":[36],"challenges":[39],"with":[40],"these":[41],"how":[44],"to":[45],"extract":[46],"tables":[47],"from":[48],"them.":[49,101],"The":[50],"paper":[51],"discusses":[52],"a":[53,68],"new":[54],"system":[55,87],"table":[57,78],"structure":[58],"recognition":[59],"untagged":[61],"documents.":[63],"It":[64],"formulated":[66],"as":[67],"set":[69],"configurable":[71],"parameters":[72],"ad-hoc":[74],"heuristics":[75],"recovering":[77],"cells.":[79],"We":[80],"consider":[81],"two":[82],"different":[83],"configurations":[84],"demonstrate":[89],"experimental":[90],"results":[91],"based":[92],"on":[93],"existing":[95],"competition":[96],"dataset":[97],"both":[99]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
