{"id":"https://openalex.org/W2974895816","doi":"https://doi.org/10.1145/3342558.3345409","title":"XLIndy","display_name":"XLIndy","publication_year":2019,"publication_date":"2019-09-19","ids":{"openalex":"https://openalex.org/W2974895816","doi":"https://doi.org/10.1145/3342558.3345409","mag":"2974895816"},"language":"en","primary_location":{"id":"doi:10.1145/3342558.3345409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/175627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085983831","display_name":"Elvis Koci","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Elvis Koci","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048883150","display_name":"Dana Kuban","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dana Kuban","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004451742","display_name":"Nico Luettig","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nico Luettig","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034724138","display_name":"Dominik Olwig","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Olwig","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000229374","display_name":"Maik Thiele","orcid":"https://orcid.org/0000-0002-1665-977X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maik Thiele","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038147189","display_name":"Julius Gonsior","orcid":"https://orcid.org/0000-0002-5985-4348"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius Gonsior","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063512642","display_name":"Wolfgang Lehner","orcid":"https://orcid.org/0000-0001-8107-2775"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Lehner","raw_affiliation_strings":["Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t Informatik, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067693515","display_name":"Oscar Romero","orcid":"https://orcid.org/0000-0001-6350-8328"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Oscar Romero","raw_affiliation_strings":["Departament d'Enginyeria de Serveis i Sistemes d'Informaci\u00f3, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTech, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Departament d'Enginyeria de Serveis i Sistemes d'Informaci\u00f3, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTech, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5085983831"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":2.0075,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87111018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11875","display_name":"Statistics Education and Methodologies","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.989799976348877,"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":0.8689322471618652},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7181450128555298},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6266359090805054},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5452379584312439},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.515421986579895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48492270708084106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48307040333747864},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.446901798248291},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4361763894557953},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37717318534851074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36879390478134155},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3128458857536316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3101411759853363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689322471618652},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7181450128555298},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6266359090805054},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5452379584312439},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.515421986579895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48492270708084106},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48307040333747864},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.446901798248291},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4361763894557953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37717318534851074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36879390478134155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3128458857536316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3101411759853363},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3342558.3345409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/175627","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/175627","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/175627","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/175627","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1579695396","https://openalex.org/W1974329121","https://openalex.org/W1976022204","https://openalex.org/W1982134088","https://openalex.org/W2000784509","https://openalex.org/W2038340833","https://openalex.org/W2048282669","https://openalex.org/W2080334712","https://openalex.org/W2098516643","https://openalex.org/W2550378979","https://openalex.org/W2618604729","https://openalex.org/W2747850582","https://openalex.org/W2767419415","https://openalex.org/W2810376801","https://openalex.org/W2901585524","https://openalex.org/W3003968453","https://openalex.org/W3003988402","https://openalex.org/W3173700007","https://openalex.org/W4230392236"],"related_works":["https://openalex.org/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W3113257914","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W4238373172"],"abstract_inverted_index":{"Over":[0],"the":[1,85,102,126],"years,":[2],"spreadsheets":[3,21],"have":[4],"established":[5],"their":[6],"presence":[7],"in":[8,60,73,125],"many":[9],"domains,":[10],"including":[11],"business,":[12],"government,":[13],"and":[14,24,28,42,70,79,89,105,107,120,143],"science.":[15],"However,":[16],"challenges":[17],"arise":[18],"due":[19],"to":[20,39,117],"being":[22],"partially-structured":[23],"carrying":[25],"implicit":[26],"(visual":[27],"textual)":[29],"information.":[30,45],"This":[31,93],"translates":[32],"into":[33],"a":[34,50,55,76],"bottleneck,":[35],"when":[36],"it":[37],"comes":[38],"automatic":[40],"analysis":[41],"extraction":[43],"of":[44],"Therefore,":[46],"we":[47],"present":[48],"XLIndy,":[49],"Microsoft":[51],"Excel":[52],"add-in":[53],"with":[54],"machine":[56],"learning":[57],"back-end,":[58],"written":[59],"Python.":[61],"It":[62],"showcases":[63],"our":[64],"novel":[65],"methods":[66],"for":[67,132],"layout":[68,104],"inference":[69],"table":[71],"recognition":[72],"spreadsheets.":[74],"For":[75],"selected":[77],"task":[78],"method,":[80],"users":[81,98],"can":[82,99,129],"visually":[83],"inspect":[84],"results,":[86],"change":[87],"configurations,":[88],"compare":[90],"different":[91],"runs.":[92],"enables":[94],"iterative":[95],"fine-tuning.":[96],"Additionally,":[97],"manually":[100],"revise":[101],"predicted":[103],"tables,":[106],"subsequently":[108],"save":[109],"them":[110],"as":[111,141],"annotations.":[112],"The":[113],"latter":[114],"is":[115],"used":[116],"measure":[118],"performance":[119],"(re-)train":[121],"classifiers.":[122],"Finally,":[123],"data":[124],"recognized":[127],"tables":[128],"be":[130],"extracted":[131],"further":[133],"processing.":[134],"XLIndy":[135],"supports":[136],"several":[137],"standard":[138],"formats,":[139],"such":[140],"CSV":[142],"JSON.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-09-26T00:00:00"}
