{"id":"https://openalex.org/W4391093424","doi":"https://doi.org/10.1109/bigdata59044.2023.10386125","title":"Advancements in Financial Document Structure Extraction: Insights from Five Years of FinTOC (2019-2023)","display_name":"Advancements in Financial Document Structure Extraction: Insights from Five Years of FinTOC (2019-2023)","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093424","doi":"https://doi.org/10.1109/bigdata59044.2023.10386125"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053661888","display_name":"Juyeon Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I47431100","display_name":"Dassault Syst\u00e8mes (France)","ror":"https://ror.org/038sc5x72","country_code":"FR","type":"company","lineage":["https://openalex.org/I47431100"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Juyeon Kang","raw_affiliation_strings":["3DS Outscale,Saint-Cloud,France","3DS Outscale, Saint-Cloud, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"3DS Outscale,Saint-Cloud,France","institution_ids":["https://openalex.org/I47431100"]},{"raw_affiliation_string":"3DS Outscale, Saint-Cloud, France","institution_ids":["https://openalex.org/I47431100"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114120404","display_name":"Mauli Mehulkumar Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mauli Mehulkumar Patel","raw_affiliation_strings":["NITK Surathkal,Dept. of Information Technology,Surathkal,India","Dept. of Information Technology, NITK Surathkal, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NITK Surathkal,Dept. of Information Technology,Surathkal,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"Dept. of Information Technology, NITK Surathkal, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859781","display_name":"Anushka Agrawal","orcid":"https://orcid.org/0009-0004-6941-8277"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anushka Agrawal","raw_affiliation_strings":["NITK Surathkal,Dept. of Information Technology,Surathkal,India","Dept. of Information Technology, NITK Surathkal, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NITK Surathkal,Dept. of Information Technology,Surathkal,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"Dept. of Information Technology, NITK Surathkal, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093759945","display_name":"Simhadri Sevitha","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Simhadri Sevitha","raw_affiliation_strings":["NITK Surathkal,Dept. of Information Technology,Surathkal,India","Dept. of Information Technology, NITK Surathkal, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NITK Surathkal,Dept. of Information Technology,Surathkal,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"Dept. of Information Technology, NITK Surathkal, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019493692","display_name":"Rangasetty Srinivasa","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R Srinivasa","raw_affiliation_strings":["NITK Surathkal,Dept. of Information Technology,Surathkal,India","Dept. of Information Technology, NITK Surathkal, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NITK Surathkal,Dept. of Information Technology,Surathkal,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"Dept. of Information Technology, NITK Surathkal, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034528095","display_name":"Sandra Bellato","orcid":null},"institutions":[{"id":"https://openalex.org/I47431100","display_name":"Dassault Syst\u00e8mes (France)","ror":"https://ror.org/038sc5x72","country_code":"FR","type":"company","lineage":["https://openalex.org/I47431100"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sandra Bellato","raw_affiliation_strings":["3DS Outscale,Saint-Cloud,France","3DS Outscale, Saint-Cloud, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"3DS Outscale,Saint-Cloud,France","institution_ids":["https://openalex.org/I47431100"]},{"raw_affiliation_string":"3DS Outscale, Saint-Cloud, France","institution_ids":["https://openalex.org/I47431100"]}]},{"author_position":"middle","author":{"id":null,"display_name":"M Anand Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M Anand Kumar","raw_affiliation_strings":["NITK Surathkal,Dept. of Information Technology,Surathkal,India","Dept. of Information Technology, NITK Surathkal, Surathkal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NITK Surathkal,Dept. of Information Technology,Surathkal,India","institution_ids":["https://openalex.org/I11880225"]},{"raw_affiliation_string":"Dept. of Information Technology, NITK Surathkal, Surathkal, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111116040","display_name":"Ngawang Dempa Tsang","orcid":null},"institutions":[{"id":"https://openalex.org/I47431100","display_name":"Dassault Syst\u00e8mes (France)","ror":"https://ror.org/038sc5x72","country_code":"FR","type":"company","lineage":["https://openalex.org/I47431100"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ngawang Dempa Tsang","raw_affiliation_strings":["3DS Outscale,Saint-Cloud,France","3DS Outscale, Saint-Cloud, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"3DS Outscale,Saint-Cloud,France","institution_ids":["https://openalex.org/I47431100"]},{"raw_affiliation_string":"3DS Outscale, Saint-Cloud, France","institution_ids":["https://openalex.org/I47431100"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093759946","display_name":"Mo El-Haj","orcid":null},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mo El-Haj","raw_affiliation_strings":["Lancaster University,Lancaster,UK","Lancaster University, Lancaster, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University,Lancaster,UK","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"Lancaster University, Lancaster, UK","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2839","last_page":"2844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9952999949455261,"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"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9952999949455261,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9807000160217285,"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/T10028","display_name":"Topic Modeling","score":0.9689000248908997,"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/computer-science","display_name":"Computer science","score":0.6720620393753052},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5179026126861572},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.508141279220581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48756688833236694},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.48666292428970337},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4471622705459595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4363471269607544},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4329971373081207},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.35703492164611816},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3563191294670105},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34288865327835083},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10233378410339355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720620393753052},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5179026126861572},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.508141279220581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48756688833236694},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.48666292428970337},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4471622705459595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4363471269607544},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4329971373081207},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.35703492164611816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3563191294670105},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34288865327835083},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10233378410339355},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386125","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:215880","is_oa":false,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/215880/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"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":"Contribution in Book/Report/Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W48722175","https://openalex.org/W1866900365","https://openalex.org/W1998037981","https://openalex.org/W2765085336","https://openalex.org/W2785634898","https://openalex.org/W2890174976","https://openalex.org/W3003711898","https://openalex.org/W3113753692","https://openalex.org/W3120704476","https://openalex.org/W3121286774","https://openalex.org/W3214074647","https://openalex.org/W4290927927","https://openalex.org/W4312937942","https://openalex.org/W4376654343","https://openalex.org/W4380434509","https://openalex.org/W4389524558","https://openalex.org/W6639441442","https://openalex.org/W6770609468","https://openalex.org/W6783407162","https://openalex.org/W6783842662","https://openalex.org/W6787735463","https://openalex.org/W6788599849","https://openalex.org/W6788661182","https://openalex.org/W6788913622","https://openalex.org/W7008736292","https://openalex.org/W7028686469"],"related_works":["https://openalex.org/W2348886128","https://openalex.org/W2388067091","https://openalex.org/W2367656648","https://openalex.org/W2350200549","https://openalex.org/W2362132076","https://openalex.org/W2965396777","https://openalex.org/W2389168924","https://openalex.org/W2067294484","https://openalex.org/W4280593102","https://openalex.org/W2368651715"],"abstract_inverted_index":{"In":[0],"this":[1],"comprehensive":[2],"paper,":[3],"we":[4],"present":[5],"a":[6,22,35],"detailed":[7],"overview":[8],"of":[9,24,38,45,57,71,105,116,131,140,149,176,186],"the":[10,39,43,55,58,69,77,84,96,102,114,128,138,144,147,159,166,173,177,182,187],"Financial":[11,59],"Table":[12],"Of":[13],"Content":[14],"extraction":[15],"shared":[16,188],"task":[17],"series,":[18,52],"FinTOC,":[19],"conducted":[20],"over":[21],"span":[23],"five":[25],"years":[26],"from":[27,109,118],"2019":[28],"to":[29,100,122],"2023.":[30],"This":[31],"paper":[32],"serves":[33],"as":[34],"retrospective":[36],"analysis":[37,81,151],"key":[40],"developments":[41],"in":[42,67,76,152,164,180],"field":[44],"financial":[46,78,110,153],"document":[47,154],"structure":[48],"extraction.":[49],"The":[50],"FinTOC":[51],"hosted":[53],"within":[54],"framework":[56],"Narrative":[60],"Processing":[61,74],"(FNP)":[62],"workshop,":[63],"has":[64],"been":[65],"instrumental":[66],"shaping":[68],"landscape":[70],"Natural":[72],"Language":[73],"(NLP)":[75],"domain.":[79],"Our":[80],"delves":[82],"into":[83],"diverse":[85],"methodologies":[86],"proposed":[87],"by":[88,143,162],"participants":[89,163],"across":[90],"all":[91],"editions,":[92],"shedding":[93],"light":[94],"on":[95],"innovative":[97],"strategies":[98],"employed":[99],"tackle":[101],"intricate":[103],"challenge":[104],"extracting":[106],"structured":[107],"information":[108],"documents.":[111],"We":[112,156],"explore":[113],"evolution":[115],"techniques,":[117],"traditional":[119],"rule-based":[120],"approaches":[121],"cutting-edge":[123],"deep":[124],"learning":[125],"models,":[126],"showcasing":[127,172],"dynamic":[129],"nature":[130],"NLP":[132,178],"advancements.":[133],"Furthermore,":[134],"our":[135],"study":[136],"investigates":[137],"introduction":[139],"multilingual":[141],"datasets":[142],"organizers,":[145],"highlighting":[146],"importance":[148],"cross-lingual":[150],"processing.":[155],"also":[157],"examine":[158],"contributions":[160],"made":[161],"augmenting":[165],"training":[167,189],"data":[168],"with":[169],"external":[170],"sources,":[171],"collaborative":[174],"spirit":[175],"community":[179],"enhancing":[181],"quality":[183],"and":[184],"size":[185],"dataset.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
