{"id":"https://openalex.org/W4323076031","doi":"https://doi.org/10.1007/s42979-022-01659-z","title":"Flexible Hybrid Table Recognition and Semantic Interpretation System","display_name":"Flexible Hybrid Table Recognition and Semantic Interpretation System","publication_year":2023,"publication_date":"2023-03-04","ids":{"openalex":"https://openalex.org/W4323076031","doi":"https://doi.org/10.1007/s42979-022-01659-z"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-022-01659-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01659-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01659-z.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01659-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084431990","display_name":"Marcin Namys\u0142","orcid":"https://orcid.org/0000-0001-7066-1726"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marcin Namys\u0142","raw_affiliation_strings":["Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7066-1726","affiliations":[{"raw_affiliation_string":"Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074893935","display_name":"A. Esser","orcid":"https://orcid.org/0000-0002-5974-2637"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander M. Esser","raw_affiliation_strings":["University of Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027761977","display_name":"Sven Behnke","orcid":"https://orcid.org/0000-0002-5040-7525"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Behnke","raw_affiliation_strings":["Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103573586","display_name":"Joachim K\u00f6hler","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joachim K\u00f6hler","raw_affiliation_strings":["Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Intelligent Systems, University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"NetMedia, Fraunhofer IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084431990"],"corresponding_institution_ids":["https://openalex.org/I135140700","https://openalex.org/I4210144576"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.4881,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57379849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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/T11719","display_name":"Data Quality and Management","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9684000015258789,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8237587213516235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042277693748474},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5180994868278503},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.507096529006958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5042606592178345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4932531714439392},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.481610506772995},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4732057452201843},{"id":"https://openalex.org/keywords/semantic-interpretation","display_name":"Semantic interpretation","score":0.4537622332572937},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44475695490837097},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.42494815587997437},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.41312333941459656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40335407853126526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39702802896499634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36703118681907654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17520666122436523}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8237587213516235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042277693748474},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5180994868278503},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.507096529006958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042606592178345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4932531714439392},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.481610506772995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4732057452201843},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.4537622332572937},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44475695490837097},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.42494815587997437},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.41312333941459656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40335407853126526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39702802896499634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36703118681907654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17520666122436523},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s42979-022-01659-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01659-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01659-z.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/446548","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/446548","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s42979-022-01659-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-022-01659-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-022-01659-z.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2162410311","display_name":null,"funder_award_id":"836 885","funder_id":"https://openalex.org/F4320321773","funder_display_name":"Fraunhofer-Gesellschaft"}],"funders":[{"id":"https://openalex.org/F4320321773","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4323076031.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W2001642682","https://openalex.org/W2009659675","https://openalex.org/W2020057462","https://openalex.org/W2022351003","https://openalex.org/W2060507674","https://openalex.org/W2061832930","https://openalex.org/W2108598243","https://openalex.org/W2117462434","https://openalex.org/W2126667706","https://openalex.org/W2133059825","https://openalex.org/W2137998699","https://openalex.org/W2142809404","https://openalex.org/W2327315803","https://openalex.org/W2549139847","https://openalex.org/W2786162033","https://openalex.org/W2798546256","https://openalex.org/W2889497954","https://openalex.org/W2951621897","https://openalex.org/W2987932197","https://openalex.org/W2991486293","https://openalex.org/W3003496674","https://openalex.org/W3004042913","https://openalex.org/W3014641072","https://openalex.org/W3023408402","https://openalex.org/W3034997246","https://openalex.org/W3035140194","https://openalex.org/W3082424964","https://openalex.org/W3093907107","https://openalex.org/W3198118332","https://openalex.org/W3202465222","https://openalex.org/W3216781819","https://openalex.org/W4200474128","https://openalex.org/W4210252045","https://openalex.org/W4304013646"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W2088988140","https://openalex.org/W2803103875","https://openalex.org/W2103019253","https://openalex.org/W2951529875","https://openalex.org/W2154798751"],"abstract_inverted_index":{"Abstract":[0],"Extracting":[1],"information":[2,182,235],"from":[3,113,224,237,246],"documents":[4,84,174],"containing":[5],"quantitative":[6],"data":[7,210,223],"in":[8,85,132,144,169,185,200],"tabular":[9],"format":[10,87],"is":[11,70,183],"an":[12,125],"important":[13],"but":[14],"still":[15],"unsolved":[16],"task":[17],"due":[18],"to":[19,28,36,216],"the":[20,74,83,98,110,128,133,141,170,180,201,241],"heterogeneity":[21],"of":[22,49,140,188],"document":[23],"layouts.":[24,78],"This":[25,39],"work":[26],"aims":[27],"take":[29],"a":[30,34,42,50,56,62,147,157,186],"step":[31],"toward":[32],"developing":[33],"solution":[35],"this":[37],"problem.":[38],"paper":[40],"proposes":[41],"flexible,":[43],"hybrid":[44],"table":[45,53,77,119,153,189],"extraction":[46,154,236],"system":[47,69,96,155,193],"consisting":[48],"deep":[51],"learning-based":[52],"detection":[54],"module,":[55],"heuristic-based":[57],"structure":[58],"recognition":[59],"method,":[60],"and":[61,72,88,101,116,136,179,211,221,244],"graph-based":[63],"semantic":[64],"interpretation":[65,120],"component.":[66],"The":[67,94,191],"proposed":[68,95,142],"modular":[71],"supports":[73],"most":[75],"frequent":[76],"Moreover,":[79,122],"it":[80],"handles":[81],"both":[82],"image":[86],"PDF":[89],"files":[90],"with":[91,106,127,146,197],"embedded":[92],"text.":[93],"outperforms":[97],"baseline":[99],"method":[100,143],"achieves":[102,156,194],"results":[103,139,195,245],"on":[104,109,208,234],"par":[105],"state-of-the-art":[107],"approaches":[108],"challenging":[111],"benchmarks":[112],"ICDAR":[114,117],"2013":[115],"2019":[118],"competitions.":[121],"we":[123,239],"correct":[124],"issue":[126],"evaluation":[129,242],"script":[130],"used":[131],"latter":[134],"competition":[135],"report":[137],"extended":[138],"comparison":[145],"leading":[148,198],"commercial":[149],"product.":[150],"Finally,":[151],"our":[152,219,247],"high":[158],"F":[159],"$$_1$$":[160],"<mml:math":[161],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[162],"<mml:msub>":[163],"<mml:mrow/>":[164],"<mml:mn>1</mml:mn>":[165],"</mml:msub>":[166],"</mml:math>":[167],"score":[168],"scenario":[171],"where":[172],"raw":[173],"are":[175],"given":[176],"as":[177],"input":[178],"targeted":[181],"contained":[184],"subset":[187],"columns.":[190],"presented":[192],"competitive":[196],"methods":[199],"field.":[202],"It":[203],"has":[204],"already":[205],"been":[206],"evaluated":[207],"general-purpose":[209],"biomedical":[212],"benchmarks.":[213],"We":[214],"intend":[215],"continuously":[217],"improve":[218],"approach":[220],"process":[222],"other":[225],"domains,":[226],"e.g.,":[227],"financial":[228],"documents.":[229],"To":[230],"support":[231],"future":[232],"research":[233],"documents,":[238],"make":[240],"scripts":[243],"experiments":[248],"publicly":[249],"available":[250],"at":[251],"https://github.com/mnamysl/tabrec-sncs":[252],".":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-03-05T00:00:00"}