{"id":"https://openalex.org/W4400368645","doi":"https://doi.org/10.1142/s0218001424590122","title":"Configurable Customized Information Extraction and Processing Pipeline","display_name":"Configurable Customized Information Extraction and Processing Pipeline","publication_year":2024,"publication_date":"2024-07-05","ids":{"openalex":"https://openalex.org/W4400368645","doi":"https://doi.org/10.1142/s0218001424590122"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001424590122","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424590122","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/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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seok Kim","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierce Lai","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104344474","display_name":"Dariyan Khan","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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dariyan Khan","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006877684","display_name":"Kevin Zhao","orcid":"https://orcid.org/0000-0002-2444-4816"},"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Zhao","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024525830","display_name":"Brian L. Le","orcid":"https://orcid.org/0009-0000-4062-094X"},"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Le","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100028346","display_name":"Alex Luchianov","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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Luchianov","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103094893","display_name":"Margaret K. Yu","orcid":"https://orcid.org/0000-0002-3650-2788"},"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret Yu","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Wang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), 32 Vassar Street, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100618783"],"corresponding_institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11210773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9735999703407288,"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/T11719","display_name":"Data Quality and Management","score":0.9735999703407288,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/pipeline","display_name":"Pipeline (software)","score":0.9033387899398804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8425548076629639},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7338420748710632},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.615287184715271},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5861469507217407},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.571304202079773},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5113407969474792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44408348202705383},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39903244376182556},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38195300102233887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667711317539215},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34251463413238525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33070167899131775},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1058414876461029},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08231717348098755}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.9033387899398804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425548076629639},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7338420748710632},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.615287184715271},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5861469507217407},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.571304202079773},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5113407969474792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44408348202705383},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39903244376182556},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38195300102233887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667711317539215},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34251463413238525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33070167899131775},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1058414876461029},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08231717348098755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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":1,"locations":[{"id":"doi:10.1142/s0218001424590122","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001424590122","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4379386778","https://openalex.org/W4385392748"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2148533276","https://openalex.org/W2094012830","https://openalex.org/W187246281"],"abstract_inverted_index":{"Extracting":[0],"information":[1,26],"from":[2,72],"scanned":[3],"business":[4],"documents,":[5],"while":[6,146],"a":[7,46,85,130,141],"necessary":[8],"commercial":[9,73,127],"task,":[10],"continues":[11],"to":[12,34,60,84,139,153],"be":[13],"mostly":[14],"done":[15],"manually,":[16],"requiring":[17],"significant":[18],"human":[19],"effort.":[20],"Current":[21],"solutions":[22,128],"for":[23,66],"automated":[24],"document":[25,89],"extraction":[27,38],"still":[28],"have":[29],"limited":[30],"capabilities":[31],"in":[32],"regards":[33],"user-required":[35],"customizability":[36,104],"and":[37,58,68,79,91,114,126,133],"of":[39,50,88,98,144],"dataset-specific":[40,99,115],"information,":[41],"leaving":[42],"the":[43,82,96,154],"area":[44],"as":[45],"very":[47],"active":[48],"field":[49],"research.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"modifications":[57],"improvements":[59],"our":[61,119],"previously":[62],"developed":[63],"custom":[64],"pipeline":[65,83],"extracting":[67],"tabulating":[69],"key-value":[70],"pairs":[71],"invoice":[74],"documents.":[75],"Our":[76],"design":[77],"changes":[78],"additions":[80],"adapt":[81],"wider":[86,142],"variety":[87,143],"types":[90],"use":[92],"cases,":[93],"primarily":[94],"through":[95],"implementation":[97],"configuration":[100],"files":[101],"that":[102,110,135],"promote":[103],"along":[105],"with":[106],"new":[107],"technical":[108],"modules":[109],"address":[111],"both":[112],"general":[113],"complexities.":[116],"We":[117],"compare":[118],"pipeline\u2019s":[120],"performance":[121],"against":[122],"current":[123],"machine":[124],"learning":[125],"on":[129],"real-world":[131],"dataset,":[132],"demonstrate":[134],"it":[136],"is":[137],"able":[138],"extract":[140],"fields":[145],"maintaining":[147],"competitive":[148],"or":[149],"greater":[150],"accuracies":[151],"compared":[152],"alternate":[155],"solutions.":[156]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
