{"id":"https://openalex.org/W3180901325","doi":"https://doi.org/10.1109/access.2021.3096739","title":"Multi-Layout Unstructured Invoice Documents Dataset: A Dataset for Template-Free Invoice Processing and Its Evaluation Using AI Approaches","display_name":"Multi-Layout Unstructured Invoice Documents Dataset: A Dataset for Template-Free Invoice Processing and Its Evaluation Using AI Approaches","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3180901325","doi":"https://doi.org/10.1109/access.2021.3096739","mag":"3180901325"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3096739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3096739","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09481217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09481217.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034807231","display_name":"Dipali Baviskar","orcid":"https://orcid.org/0000-0001-6351-8737"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dipali Baviskar","raw_affiliation_strings":["Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0000-0001-6351-8737","affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010638862","display_name":"Swati Ahirrao","orcid":"https://orcid.org/0000-0002-8554-2129"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swati Ahirrao","raw_affiliation_strings":["Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0000-0002-8554-2129","affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077770842","display_name":"Ketan Kotecha","orcid":"https://orcid.org/0000-0003-2653-3780"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ketan Kotecha","raw_affiliation_strings":["Symbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University), Pune, Maharashtra, India"],"raw_orcid":"https://orcid.org/0000-0003-2653-3780","affiliations":[{"raw_affiliation_string":"Symbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University), Pune, Maharashtra, India","institution_ids":["https://openalex.org/I244572783"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I244572783"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0728,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.88988693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"101494","last_page":"101512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9772999882698059,"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":0.9772999882698059,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9707000255584717,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9549000263214111,"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":0.8559421300888062},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.8466849327087402},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5798755884170532},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5162467956542969},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.509648323059082},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.4772724509239197},{"id":"https://openalex.org/keywords/invoice","display_name":"Invoice","score":0.4734896123409271},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46517229080200195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46516019105911255},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4372696280479431},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.340059369802475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3380880355834961},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.22912144660949707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559421300888062},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.8466849327087402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5798755884170532},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5162467956542969},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.509648323059082},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.4772724509239197},{"id":"https://openalex.org/C2781456945","wikidata":"https://www.wikidata.org/wiki/Q190581","display_name":"Invoice","level":2,"score":0.4734896123409271},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46517229080200195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46516019105911255},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4372696280479431},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.340059369802475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3380880355834961},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.22912144660949707},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/access.2021.3096739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3096739","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09481217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ac3115ebe1a1427cbae1b3b283bb7770","is_oa":true,"landing_page_url":"https://doaj.org/article/ac3115ebe1a1427cbae1b3b283bb7770","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 101494-101512 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3096739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3096739","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09481217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3180901325.pdf","grobid_xml":"https://content.openalex.org/works/W3180901325.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1997754546","https://openalex.org/W2028738040","https://openalex.org/W2151765755","https://openalex.org/W2516822814","https://openalex.org/W2537675719","https://openalex.org/W2768488789","https://openalex.org/W2782912507","https://openalex.org/W2789244308","https://openalex.org/W2790618693","https://openalex.org/W2912576923","https://openalex.org/W2912689473","https://openalex.org/W2916869519","https://openalex.org/W2920124529","https://openalex.org/W2935408319","https://openalex.org/W2955483668","https://openalex.org/W2956530858","https://openalex.org/W2962933419","https://openalex.org/W2963687456","https://openalex.org/W2964000578","https://openalex.org/W2965516373","https://openalex.org/W2966776429","https://openalex.org/W2973047034","https://openalex.org/W2980121369","https://openalex.org/W2981089724","https://openalex.org/W2982358276","https://openalex.org/W2986619406","https://openalex.org/W2994804941","https://openalex.org/W2995151999","https://openalex.org/W2998301900","https://openalex.org/W3003261556","https://openalex.org/W3003484198","https://openalex.org/W3003711898","https://openalex.org/W3004330198","https://openalex.org/W3006008097","https://openalex.org/W3006227201","https://openalex.org/W3027691400","https://openalex.org/W3030600301","https://openalex.org/W3082330004","https://openalex.org/W3085008468","https://openalex.org/W3091806362","https://openalex.org/W3105248300","https://openalex.org/W3109605947","https://openalex.org/W3113753692","https://openalex.org/W3122950209","https://openalex.org/W3155464240","https://openalex.org/W3198984549","https://openalex.org/W4251641598","https://openalex.org/W6759202301","https://openalex.org/W6761480002","https://openalex.org/W6766846879","https://openalex.org/W6778206941","https://openalex.org/W6783285400","https://openalex.org/W6784264348","https://openalex.org/W6786805750"],"related_works":["https://openalex.org/W2030910246","https://openalex.org/W4389912246","https://openalex.org/W4205553786","https://openalex.org/W2372366649","https://openalex.org/W3155464240","https://openalex.org/W4362731990","https://openalex.org/W1516746680","https://openalex.org/W2921654184","https://openalex.org/W2979518282","https://openalex.org/W1999203345"],"abstract_inverted_index":{"The":[0,172,194],"daily":[1],"transaction":[2],"of":[3,10,36,52,70,88,132,227],"an":[4,53],"organization":[5],"generates":[6],"a":[7,25,34,58,63,130,158,167],"vast":[8],"amount":[9],"unstructured":[11,22,45,74,113,153,161,175,192,197,238],"data":[12,23,32,133,138,169],"such":[13,41,123,208,216],"as":[14,124,209,217],"invoices":[15],"and":[16,20,90,105,129,213,219,231],"purchase":[17],"orders.":[18],"Managing":[19],"analyzing":[21],"is":[24,57,93,179,201],"costly":[26],"affair":[27],"for":[28,81,108,147,191],"the":[29,50,68,86,94,116,143,224,235,244],"organization.":[30,54],"Unstructured":[31],"has":[33,102],"wealth":[35],"hidden":[37],"valuable":[38],"information.":[39],"Extracting":[40],"insights":[42],"automatically":[43],"from":[44,73,112,152],"documents":[46,163,177,199],"can":[47,66],"significantly":[48],"increase":[49],"productivity":[51],"Thus,":[55],"there":[56],"huge":[59],"demand":[60],"to":[61,136,185],"develop":[62],"tool":[64],"that":[65],"automate":[67],"extraction":[69,151,189,206,229],"key":[71,83,110,149,187],"fields":[72,111,150],"documents.":[75,114,154,193],"Researchers":[76],"have":[77],"used":[78,103],"different":[79],"approaches":[80,135,215,233],"extracting":[82,109],"fields,":[84],"but":[85],"lack":[87,131],"annotated":[89],"high-quality":[91],"datasets":[92,107,118],"biggest":[95],"challenge.":[96],"Existing":[97],"work":[98,141,156],"in":[99,182],"this":[100],"area":[101],"standard":[104],"custom":[106],"Still,":[115],"existing":[117],"face":[119],"some":[120],"serious":[121],"challenges,":[122],"poor-quality":[125],"images,":[126],"domain-related":[127],"datasets,":[128],"validation":[134,170],"evaluate":[137],"quality.":[139],"This":[140,155],"highlights":[142],"detailed":[144],"process":[145],"flow":[146],"end-to-end":[148],"presents":[157],"high-quality,":[159],"multi-layout":[160,174,196,237],"invoice":[162,176,183,198,239],"dataset":[164,178,200],"assessed":[165],"with":[166,203,247],"statistical":[168],"technique.":[171],"proposed":[173,195,236],"highly":[180],"diverse":[181],"layouts":[184],"generalize":[186],"field":[188],"tasks":[190],"evaluated":[202],"various":[204],"feature":[205,228],"techniques":[207,230],"Glove,":[210],"Word2Vec,":[211],"FastText,":[212],"AI":[214,232],"BiLSTM":[218],"BiLSTM-CRF.":[220],"We":[221,242],"also":[222],"present":[223],"comparative":[225],"analysis":[226],"on":[234],"document":[240],"dataset.":[241],"attained":[243],"best":[245],"results":[246],"BiLSTM-CRF":[248],"model.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
