{"id":"https://openalex.org/W3155464240","doi":"https://doi.org/10.1109/access.2021.3072900","title":"Efficient Automated Processing of the Unstructured Documents Using Artificial Intelligence: A Systematic Literature Review and Future Directions","display_name":"Efficient Automated Processing of the Unstructured Documents Using Artificial Intelligence: A Systematic Literature Review and Future Directions","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3155464240","doi":"https://doi.org/10.1109/access.2021.3072900","mag":"3155464240"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3072900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3072900","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09402739.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09402739.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, India"],"raw_orcid":"https://orcid.org/0000-0001-6351-8737","affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 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, India"],"raw_orcid":"https://orcid.org/0000-0002-8554-2129","affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027988910","display_name":"Vidyasagar Potdar","orcid":"https://orcid.org/0000-0002-7292-5462"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vidyasagar Potdar","raw_affiliation_strings":["Blockchain Research and Development Laboratory, Curtin University, Perth, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blockchain Research and Development Laboratory, Curtin University, Perth, WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"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, 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, India","institution_ids":["https://openalex.org/I244572783"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.866,"has_fulltext":true,"cited_by_count":151,"citation_normalized_percentile":{"value":0.9223301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"72894","last_page":"72936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14319","display_name":"Currency Recognition and Detection","score":0.9821000099182129,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9821000099182129,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9384999871253967,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.853985071182251},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.7982436418533325},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6986497640609741},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5422043204307556},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5392436385154724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5035256743431091},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49277380108833313},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.46692749857902527},{"id":"https://openalex.org/keywords/conceptualization","display_name":"Conceptualization","score":0.43835243582725525},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4068836271762848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30537092685699463},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.20203912258148193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853985071182251},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7982436418533325},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6986497640609741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5422043204307556},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5392436385154724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5035256743431091},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49277380108833313},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.46692749857902527},{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.43835243582725525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4068836271762848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30537092685699463},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.20203912258148193},{"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3072900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3072900","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09402739.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b14796a4df204468a1fe1103f6f74b7c","is_oa":true,"landing_page_url":"https://doaj.org/article/b14796a4df204468a1fe1103f6f74b7c","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 72894-72936 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3072900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3072900","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09402739.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3155464240.pdf","grobid_xml":"https://content.openalex.org/works/W3155464240.grobid-xml"},"referenced_works_count":122,"referenced_works":["https://openalex.org/W177045304","https://openalex.org/W791527587","https://openalex.org/W1511676561","https://openalex.org/W1966631307","https://openalex.org/W1997754546","https://openalex.org/W2003996632","https://openalex.org/W2019803582","https://openalex.org/W2027883219","https://openalex.org/W2028738040","https://openalex.org/W2038941723","https://openalex.org/W2072498467","https://openalex.org/W2094070378","https://openalex.org/W2135231474","https://openalex.org/W2316779280","https://openalex.org/W2337057345","https://openalex.org/W2342299174","https://openalex.org/W2516822814","https://openalex.org/W2526903591","https://openalex.org/W2537675719","https://openalex.org/W2543875770","https://openalex.org/W2578252781","https://openalex.org/W2591911556","https://openalex.org/W2752571292","https://openalex.org/W2768488789","https://openalex.org/W2779545291","https://openalex.org/W2782912507","https://openalex.org/W2787480186","https://openalex.org/W2789244308","https://openalex.org/W2790618693","https://openalex.org/W2791164948","https://openalex.org/W2791908537","https://openalex.org/W2805420324","https://openalex.org/W2806031239","https://openalex.org/W2887178861","https://openalex.org/W2888486030","https://openalex.org/W2889198729","https://openalex.org/W2889542933","https://openalex.org/W2891117443","https://openalex.org/W2893624139","https://openalex.org/W2911600385","https://openalex.org/W2912576923","https://openalex.org/W2916349291","https://openalex.org/W2916869519","https://openalex.org/W2919466488","https://openalex.org/W2919811233","https://openalex.org/W2920124529","https://openalex.org/W2934798344","https://openalex.org/W2935408319","https://openalex.org/W2937423263","https://openalex.org/W2946108305","https://openalex.org/W2950092222","https://openalex.org/W2956037940","https://openalex.org/W2962772269","https://openalex.org/W2962788341","https://openalex.org/W2962902328","https://openalex.org/W2962933419","https://openalex.org/W2963184176","https://openalex.org/W2963687456","https://openalex.org/W2964000578","https://openalex.org/W2965009206","https://openalex.org/W2965516373","https://openalex.org/W2966776429","https://openalex.org/W2969928624","https://openalex.org/W2971987430","https://openalex.org/W2972848526","https://openalex.org/W2973047034","https://openalex.org/W2973803552","https://openalex.org/W2978202681","https://openalex.org/W2980036462","https://openalex.org/W2980121369","https://openalex.org/W2981089724","https://openalex.org/W2982358276","https://openalex.org/W2988423567","https://openalex.org/W2990036959","https://openalex.org/W2990209204","https://openalex.org/W2991587471","https://openalex.org/W2994804941","https://openalex.org/W2995151999","https://openalex.org/W2996441822","https://openalex.org/W2998301900","https://openalex.org/W3003261556","https://openalex.org/W3003484198","https://openalex.org/W3003635488","https://openalex.org/W3004051332","https://openalex.org/W3004330198","https://openalex.org/W3006008097","https://openalex.org/W3006227201","https://openalex.org/W3008574247","https://openalex.org/W3013327809","https://openalex.org/W3027691400","https://openalex.org/W3035669514","https://openalex.org/W3037272733","https://openalex.org/W3043249783","https://openalex.org/W3044761164","https://openalex.org/W3045882047","https://openalex.org/W3063584767","https://openalex.org/W3080359515","https://openalex.org/W3082330004","https://openalex.org/W3085008468","https://openalex.org/W3105625590","https://openalex.org/W3105988348","https://openalex.org/W3122721075","https://openalex.org/W3122950209","https://openalex.org/W3152332785","https://openalex.org/W3171963866","https://openalex.org/W4239198127","https://openalex.org/W4251641598","https://openalex.org/W4285719527","https://openalex.org/W4297801661","https://openalex.org/W4297814127","https://openalex.org/W6703524213","https://openalex.org/W6728995649","https://openalex.org/W6732436459","https://openalex.org/W6748206367","https://openalex.org/W6749365830","https://openalex.org/W6761480002","https://openalex.org/W6766846879","https://openalex.org/W6782320295","https://openalex.org/W6783285400","https://openalex.org/W6797216136","https://openalex.org/W6833758557","https://openalex.org/W6982521223"],"related_works":["https://openalex.org/W2766430668","https://openalex.org/W2030910246","https://openalex.org/W4389912246","https://openalex.org/W4205553786","https://openalex.org/W4385489363","https://openalex.org/W2372366649","https://openalex.org/W4362731990","https://openalex.org/W4316660311","https://openalex.org/W4206851959","https://openalex.org/W3155464240"],"abstract_inverted_index":{"The":[0,24,60,92,118,128,149],"unstructured":[1,53,83,188,202,216,249],"data":[2,221,250],"impacts":[3],"95%":[4],"of":[5,12,45,62,156,200,209,214,247],"the":[6,58,75,132,201,239,248],"organizations":[7],"and":[8,71,85,98,112,145,155,241],"costs":[9],"them":[10],"millions":[11],"dollars":[13],"annually.":[14],"If":[15],"managed":[16],"well,":[17],"it":[18],"can":[19,37],"significantly":[20],"improve":[21],"business":[22],"productivity.":[23],"traditional":[25],"information":[26,50,80,120,186,226],"extraction":[27,51,81,121],"techniques":[28,36,47,76,122,223],"are":[29,123,153],"limited":[30],"in":[31,57,139,196],"their":[32],"functionality,":[33],"but":[34],"AI-based":[35,46,177],"provide":[38,87],"a":[39,104,162,166,180,210,232,235],"better":[40],"solution.":[41],"A":[42],"thorough":[43],"investigation":[44],"for":[48,78,89,212,224,234],"automatic":[49,79],"from":[52,82,187],"documents":[54,84,189,217],"is":[55,68,161],"missing":[56],"literature.":[59],"purpose":[61],"this":[63],"Systematic":[64],"Literature":[65],"Review":[66],"(SLR)":[67],"to":[69,86,102,134,164,183,243],"recognize,":[70],"analyze":[72],"research":[73],"on":[74,107],"used":[77],"directions":[88],"future":[90],"research.":[91],"SLR":[93,174,205,229],"guidelines":[94],"proposed":[95],"by":[96],"Kitchenham":[97],"Charters":[99],"were":[100],"adhered":[101],"conduct":[103],"literature":[105],"search":[106],"various":[108,245],"databases":[109],"between":[110,238],"2010":[111],"2020.":[113],"We":[114],"found":[115],"that:":[116],"1.":[117],"existing":[119,129],"template-based":[124],"or":[125],"rule-based,":[126],"2.":[127],"methods":[130],"lack":[131],"capability":[133],"tackle":[135],"complex":[136],"document":[137],"layouts":[138,199],"real-time":[140],"situations":[141],"such":[142],"as":[143],"invoices":[144],"purchase":[146],"orders,":[147],"3.":[148],"datasets":[150],"available":[151],"publicly":[152],"task-specific":[154],"low":[157],"quality.":[158],"Hence,":[159],"there":[160],"need":[163,233],"develop":[165],"new":[167],"dataset":[168,218],"that":[169,176],"reflects":[170],"real-world":[171],"problems.":[172],"Our":[173,204,228],"discovered":[175],"approaches":[178],"have":[179],"strong":[181,220],"potential":[182],"extract":[184],"useful":[185],"automatically.":[190],"However,":[191],"they":[192],"face":[193],"certain":[194],"challenges":[195,246],"processing":[197],"multiple":[198],"documents.":[203],"brings":[206],"out":[207],"conceptualization":[208],"framework":[211],"construction":[213],"high-quality":[215],"with":[219],"validation":[222],"automated":[225],"extraction.":[227],"also":[230],"reveals":[231],"close":[236],"association":[237],"businesses":[240],"researchers":[242],"handle":[244],"analysis.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}