{"id":"https://openalex.org/W4379386778","doi":"https://doi.org/10.1142/s0218001423540137","title":"Customized Information Extraction and Processing Pipeline for Commercial Invoices","display_name":"Customized Information Extraction and Processing Pipeline for Commercial Invoices","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379386778","doi":"https://doi.org/10.1142/s0218001423540137"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001423540137","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423540137","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},"type":"article","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/A5020392326","display_name":"Pierce Lai","orcid":"https://orcid.org/0000-0002-7888-0381"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pierce Lai","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024002623","display_name":"Abhishek Mohan","orcid":"https://orcid.org/0000-0003-3552-4763"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Mohan","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618783","display_name":"Seok Kim","orcid":"https://orcid.org/0000-0003-1539-5714"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seok Kim","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012386789","display_name":"Jung Soo Victor Chu","orcid":"https://orcid.org/0000-0001-7943-4853"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jung Soo Victor Chu","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087978393","display_name":"Sam Lee","orcid":"https://orcid.org/0000-0002-6805-4051"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Lee","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039193278","display_name":"Prabhakar Kafle","orcid":null},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prabhakar Kafle","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064872913","display_name":"Patrick Wang","orcid":"https://orcid.org/0000-0003-3117-8189"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Wang","raw_affiliation_strings":["CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, 32 Vassar St, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020392326"],"corresponding_institution_ids":["https://openalex.org/I126820664"],"apc_list":null,"apc_paid":null,"fwci":0.1235,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37977704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"37","issue":"09","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9872000217437744,"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":0.9872000217437744,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9682999849319458,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9574999809265137,"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/pipeline","display_name":"Pipeline (software)","score":0.8638856410980225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045074939727783},{"id":"https://openalex.org/keywords/invoice","display_name":"Invoice","score":0.7371100783348083},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6605229377746582},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5755153298377991},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5659505724906921},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5511533617973328},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4623473882675171},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4546724259853363},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4302142262458801},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42973199486732483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3433583080768585},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3214288055896759}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8638856410980225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045074939727783},{"id":"https://openalex.org/C2781456945","wikidata":"https://www.wikidata.org/wiki/Q190581","display_name":"Invoice","level":2,"score":0.7371100783348083},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6605229377746582},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5755153298377991},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5659505724906921},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5511533617973328},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4623473882675171},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4546724259853363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4302142262458801},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42973199486732483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3433583080768585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3214288055896759},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001423540137","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001423540137","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1986011338","https://openalex.org/W2040102554","https://openalex.org/W2591403015","https://openalex.org/W2769851464","https://openalex.org/W2946991228","https://openalex.org/W3138679955","https://openalex.org/W3178709966","https://openalex.org/W3216666189","https://openalex.org/W4229331846","https://openalex.org/W4237814560"],"related_works":["https://openalex.org/W2014638835","https://openalex.org/W2392846042","https://openalex.org/W1537287887","https://openalex.org/W3198095220","https://openalex.org/W2265899139","https://openalex.org/W4254961695","https://openalex.org/W2902113098","https://openalex.org/W4206165709","https://openalex.org/W2356275634","https://openalex.org/W4281745092"],"abstract_inverted_index":{"Extracting":[0],"information":[1,30],"from":[2,77],"scanned":[3],"invoices":[4],"and":[5,32,47,72,90,114],"other":[6],"commercial":[7,78],"documents,":[8],"a":[9,65,98,110],"critical":[10],"component":[11],"of":[12,28,120],"corporate":[13],"function,":[14],"typically":[15],"requires":[16],"significant":[17],"manual":[18,38,121],"processing.":[19],"Much":[20],"research":[21],"has":[22],"been":[23],"conducted":[24],"in":[25,54],"the":[26,37,82,106,118,134],"field":[27],"automated":[29],"extraction":[31],"document":[33,42,86],"processing":[34],"to":[35,97,124,138],"alleviate":[36],"resources":[39],"used":[40],"for":[41,56,70],"analysis,":[43],"but":[44],"resultant":[45],"literature":[46],"commercially":[48,111],"available":[49,112],"products":[50],"have":[51],"demonstrated":[52],"limitations":[53],"customizability":[55],"identifying":[57],"specific":[58],"information.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,103],"propose":[64],"customized":[66],"machine":[67],"learning-based":[68],"pipeline":[69,83,107],"extracting":[71],"tabulating":[73],"relevant":[74],"key\u2013value":[75,91],"pairs":[76],"invoice":[79,100,126],"documents.":[80,127],"Specifically,":[81],"combines":[84],"general":[85],"understanding,":[87],"OCR":[88],"extraction,":[89],"matching":[92],"with":[93],"custom":[94],"rules":[95],"pertaining":[96],"provided":[99],"dataset.":[101],"Then,":[102],"demonstrate":[104],"that":[105],"greatly":[108],"outperforms":[109],"product":[113],"can":[115],"significantly":[116],"reduce":[117],"amount":[119],"labor":[122],"required":[123],"process":[125],"Future":[128],"work":[129],"will":[130],"focus":[131],"on":[132,141],"generalizing":[133],"pipeline,":[135],"so":[136],"as":[137],"apply":[139],"it":[140],"more":[142],"varied":[143],"datasets.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}