{"id":"https://openalex.org/W2087079057","doi":"https://doi.org/10.1145/1166160.1166190","title":"Meta-algorithmic systems for document classification","display_name":"Meta-algorithmic systems for document classification","publication_year":2006,"publication_date":"2006-10-10","ids":{"openalex":"https://openalex.org/W2087079057","doi":"https://doi.org/10.1145/1166160.1166190","mag":"2087079057"},"language":"en","primary_location":{"id":"doi:10.1145/1166160.1166190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","raw_type":"proceedings-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/A5022519243","display_name":"Steven J. Simske","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven J. Simske","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066932343","display_name":"David W. Wright","orcid":"https://orcid.org/0000-0002-5124-8044"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David W. Wright","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091740796","display_name":"Margaret Sturgill","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret Sturgill","raw_affiliation_strings":["Hewlett-Packard Labs","Hewlett-Packard Labs,#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022519243"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":1.3552,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84357982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996999979019165,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9937999844551086,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9911999702453613,"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":0.8336751461029053},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7732155323028564},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5645707249641418},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.5476452708244324},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5302015542984009},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4482741355895996},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4308684468269348},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4113992750644684},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3478083610534668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3322659730911255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336751461029053},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7732155323028564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5645707249641418},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5476452708244324},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5302015542984009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4482741355895996},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4308684468269348},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4113992750644684},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3478083610534668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3322659730911255},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1166160.1166190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332688","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1538372379","https://openalex.org/W1988790447","https://openalex.org/W2022268612","https://openalex.org/W2030646297","https://openalex.org/W2118020653","https://openalex.org/W2125493259","https://openalex.org/W2143052270","https://openalex.org/W6632312326"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W2110028391","https://openalex.org/W54497855"],"abstract_inverted_index":{"To":[0],"address":[1,89],"cost":[2],"and":[3,37,81,98,100,152,155,163,211],"regulatory":[4],"concerns,":[5],"many":[6,111,127],"businesses":[7],"are":[8,52,86],"converting":[9],"paper-based":[10],"elements":[11],"of":[12,23,59,107,128,167,169,178,197],"their":[13,95],"workflows":[14,66],"into":[15,30],"fully":[16],"electronic":[17],"flows":[18],"that":[19,201],"use":[20],"the":[21,24,27,42,110,146,165,170,176,179],"content":[22],"documents.":[25],"Scanning":[26],"document":[28,113,137,204],"contents":[29],"workflows,":[31],"however,":[32],"is":[33],"a":[34,53,104,195],"manual,":[35],"error-prone,":[36],"costly":[38],"process":[39,45],"especially":[40],"when":[41],"data":[43],"extraction":[44],"requires":[46],"high":[47,105],"accuracy.":[48],"These":[49,143],"manual":[50],"costs":[51],"primary":[54],"barrier":[55],"to":[56,88,125,160,164,209,218],"widespread":[57],"adoption":[58],"distributed":[60],"capture":[61],"solutions":[62,77],"for":[63,136,194],"business":[64,118],"critical":[65,119],"such":[67,187],"as":[68,188],"insurance":[69],"claims,":[70],"medical":[71],"records,":[72],"or":[73],"loan":[74],"applications.":[75],"Software":[76],"using":[78,139],"artificial":[79],"intelligence":[80],"natural":[82],"language":[83],"processing":[84],"techniques":[85,186],"emerging":[87],"these":[90,117,129],"needs,":[91],"but":[92],"each":[93],"have":[94,102],"individual":[96,171,180,203],"strengths":[97],"weaknesses,":[99],"none":[101],"demonstrated":[103],"level":[106],"accuracy":[108],"across":[109],"unstructured":[112],"types":[114],"included":[115],"in":[116,149,158],"workflows.":[120],"This":[121,173],"paper":[122,174],"describes":[123],"how":[124],"overcome":[126],"limitations":[130],"by":[131,207,216],"intelligently":[132],"combining":[133],"multiple":[134,150],"approaches":[135],"classification":[138],"meta-algorithmic":[140],"design":[141],"patterns.":[142],"patterns":[144,200],"explore":[145],"error":[147,205,214],"space":[148],"engines,":[151],"provide":[153],"improved":[154],"emergent":[156],"results":[157,177,193],"comparison":[159],"voting":[161],"schemes":[162],"output":[166],"any":[168],"engines.":[172],"considers":[175],"engines":[181],"along":[182],"with":[183],"traditional":[184],"combinatorial":[185],"voting,":[189],"before":[190],"describing":[191],"prototype":[192],"variety":[196],"novel":[198],"metaalgorithmic":[199],"reduce":[202,212],"rates":[206,215],"up":[208,217],"13%":[210],"system":[213],"38%.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}