{"id":"https://openalex.org/W4408062205","doi":"https://doi.org/10.5220/0013261000003905","title":"Deep Learning for Effective Classification and Information Extraction of Financial Documents","display_name":"Deep Learning for Effective Classification and Information Extraction of Financial Documents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408062205","doi":"https://doi.org/10.5220/0013261000003905"},"language":"en","primary_location":{"id":"doi:10.5220/0013261000003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261000003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013261000003905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116465325","display_name":"Valentin-Adrian Serbanescu","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Valentin-Adrian Serbanescu","raw_affiliation_strings":["Department of Artificial Intelligence, Bernoulli Institute, University of Groningen, 9747 AG Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Bernoulli Institute, University of Groningen, 9747 AG Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017566697","display_name":"Maruf A. Dhali","orcid":"https://orcid.org/0000-0002-7548-3858"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maruf Dhali","raw_affiliation_strings":["Department of Artificial Intelligence, Bernoulli Institute, University of Groningen, 9747 AG Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Bernoulli Institute, University of Groningen, 9747 AG Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":1.3663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78666012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"749","last_page":"756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9725000262260437,"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":0.9725000262260437,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845503449440002},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5145108699798584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48354148864746094},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4367191791534424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3342050313949585},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3318154215812683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845503449440002},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5145108699798584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48354148864746094},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4367191791534424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3342050313949585},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3318154215812683},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0013261000003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261000003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/8434f657-c1da-48e5-a676-4b2e51b580c6","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/8434f657-c1da-48e5-a676-4b2e51b580c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Serbanescu, V-A & Dhali, M A 2025, Deep Learning for Effective Classification and Information Extraction of Financial Documents. in M Castrillon-Santana, M De Marsico & A Fred (eds), Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods. vol. 1, SciTePress, Porto, Portugal, pp. 749-756. https://doi.org/10.5220/0013261000003905","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire/8434f657-c1da-48e5-a676-4b2e51b580c6","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/8434f657-c1da-48e5-a676-4b2e51b580c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Serbanescu, V-A & Dhali, M A 2025, Deep Learning for Effective Classification and Information Extraction of Financial Documents. in M Castrillon-Santana, M De Marsico & A Fred (eds), Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods. vol. 1, SciTePress, Porto, Portugal, pp. 749-756. https://doi.org/10.5220/0013261000003905","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0013261000003905","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013261000003905","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"The":[0,101],"financial":[1,57,73,108,120,178],"and":[2,30,32,42,50,55,88,93,96,105,115,138,144,154,165],"accounting":[3],"sectors":[4],"are":[5,103],"encountering":[6],"increased":[7],"demands":[8],"to":[9,47],"effectively":[10,48],"manage":[11],"large":[12],"volumes":[13],"of":[14,133,152,177],"documents":[15,109,121,179],"in":[16,36,122,128,147,180],"today\u2019s":[17],"digital":[18],"environment.":[19],"Meeting":[20],"this":[21],"demand":[22],"is":[23],"crucial":[24],"for":[25,90,98,173],"accurate":[26],"archiving,":[27],"maintaining":[28],"efficiency":[29],"competitiveness,":[31],"ensuring":[33],"operational":[34],"excellence":[35],"the":[37,69,158,162,168,175,181],"industry.":[38],"This":[39,80],"study":[40],"proposes":[41],"analyzes":[43],"machine":[44],"learning-based":[45],"pipelines":[46],"classify":[49],"extract":[51],"information":[52,99],"from":[53,110],"scanned":[54],"photographed":[56],"documents,":[58,167],"such":[59],"as":[60],"invoices,":[61],"receipts,":[62],"bank":[63],"statements,":[64],"etc.":[65],"It":[66],"also":[67],"addresses":[68],"challenges":[70,159],"associated":[71],"with":[72,119,135],"document":[74,91],"processing":[75,176],"using":[76],"deep":[77],"learning":[78],"techniques.":[79],"research":[81],"explores":[82],"several":[83],"models,":[84],"including":[85],"LeNet5,":[86],"VGG19,":[87],"MobileNetV2":[89,126],"classification":[92,129],"RoBERTa,":[94],"LayoutLMv3,":[95],"GraphDoc":[97],"extraction.":[100],"models":[102],"trained":[104],"tested":[106],"on":[107],"previously":[111],"available":[112],"benchmark":[113],"datasets":[114],"a":[116],"new":[117],"dataset":[118,164],"Romanian.":[123],"Results":[124],"show":[125],"excels":[127],"tasks":[130,149],"(with":[131,150],"accuracies":[132],"99.24%":[134],"data":[136],"augmentation":[137],"93.33%":[139],"without":[140],"augmentation),":[141],"while":[142],"RoBERTa":[143],"LayoutLMv3":[145],"lead":[146],"extraction":[148],"F1-scores":[151],"0.7761":[153],"0.7426,":[155],"respectively).":[156],"Despite":[157],"posed":[160],"by":[161],"imbalanced":[163],"cross-language":[166],"proposed":[169],"pipeline":[170],"shows":[171],"potential":[172],"automating":[174],"relevant":[182],"sectors.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}