{"id":"https://openalex.org/W2896049240","doi":"https://doi.org/10.1145/3264746.3264793","title":"Automatic knowledge extraction from OCR documents using hierarchical document analysis","display_name":"Automatic knowledge extraction from OCR documents using hierarchical document analysis","publication_year":2018,"publication_date":"2018-10-09","ids":{"openalex":"https://openalex.org/W2896049240","doi":"https://doi.org/10.1145/3264746.3264793","mag":"2896049240"},"language":"en","primary_location":{"id":"doi:10.1145/3264746.3264793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264746.3264793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","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/A5083502477","display_name":"Mohammad Masum","orcid":"https://orcid.org/0000-0001-9974-6950"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masum Mohammad","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010258542","display_name":"Sai Kosaraju","orcid":"https://orcid.org/0000-0002-4332-6217"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Kosaraju","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079686219","display_name":"Tanju Bayramoglu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanju Bayramoglu","raw_affiliation_strings":["GE Power"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE Power","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022993470","display_name":"Girish Modgil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Girish Modgil","raw_affiliation_strings":["GE Power"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE Power","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058010272","display_name":"Mingon Kang","orcid":"https://orcid.org/0000-0002-9565-9523"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingon Kang","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2339,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86196494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9902999997138977,"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/T10028","display_name":"Topic Modeling","score":0.9869999885559082,"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":0.8903827667236328},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7313511371612549},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.66789311170578},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6301127076148987},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5146811604499817},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5024840831756592},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4614397883415222},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.44088014960289},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4351862072944641},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43099215626716614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30695641040802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8903827667236328},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7313511371612549},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.66789311170578},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6301127076148987},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5146811604499817},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5024840831756592},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4614397883415222},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.44088014960289},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4351862072944641},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43099215626716614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30695641040802},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3264746.3264793","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264746.3264793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.kennesaw.edu:dataphdgreylit-1013","is_oa":false,"landing_page_url":"https://digitalcommons.kennesaw.edu/dataphdgreylit/12","pdf_url":null,"source":{"id":"https://openalex.org/S4377196456","display_name":"DigitalCommons - Kennesaw State University (Kennesaw State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172980758","host_organization_name":"Kennesaw State University","host_organization_lineage":["https://openalex.org/I172980758"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Published and Grey Literature from PhD Candidates","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W32002537","https://openalex.org/W1965667542","https://openalex.org/W2000672666","https://openalex.org/W2027875450","https://openalex.org/W2031837460","https://openalex.org/W2061941130","https://openalex.org/W2084458362","https://openalex.org/W2104210067","https://openalex.org/W2126502509","https://openalex.org/W2135843591","https://openalex.org/W2295585843","https://openalex.org/W2416212312","https://openalex.org/W2763279802","https://openalex.org/W2767261630","https://openalex.org/W2793696860","https://openalex.org/W2800083662","https://openalex.org/W2805072900","https://openalex.org/W2994326685","https://openalex.org/W4231856373","https://openalex.org/W4235842576","https://openalex.org/W4243227442","https://openalex.org/W4245267204","https://openalex.org/W4387316189"],"related_works":["https://openalex.org/W2357854711","https://openalex.org/W4243448361","https://openalex.org/W2051700896","https://openalex.org/W1552255772","https://openalex.org/W2111524952","https://openalex.org/W2054759342","https://openalex.org/W2016355461","https://openalex.org/W4234690372","https://openalex.org/W4239551281","https://openalex.org/W2103484298"],"abstract_inverted_index":{"Industries":[0],"can":[1,55,117],"improve":[2,56],"their":[3,103],"business":[4],"efficiency":[5],"by":[6,62,110],"analyzing":[7],"and":[8,29,100],"extracting":[9,68],"relevant":[10,46,105],"knowledge":[11,47,92,106,122],"from":[12,20,48,72,107],"large":[13,21],"numbers":[14],"of":[15,23,37,59,121,134,142],"documents.":[16,50],"Knowledge":[17],"extraction":[18,93],"manually":[19],"volume":[22],"documents":[24,74,109,135],"is":[25,75],"labor":[26],"intensive,":[27],"unscalable":[28],"challenging.":[30],"Consequently,":[31],"there":[32],"have":[33],"been":[34],"a":[35,91,124],"number":[36],"attempts":[38],"to":[39,43,78,123],"develop":[40],"intelligent":[41],"systems":[42],"automatically":[44,101],"extract":[45],"OCR":[49,73,108],"Moreover,":[51],"the":[52,57,69,129],"automatic":[53],"system":[54,94],"capability":[58],"search":[60],"engine":[61],"providing":[63],"application-specific":[64],"domain":[65],"knowledge.":[66],"However,":[67],"efficient":[70,88],"information":[71],"challenging":[76],"due":[77],"highly":[79],"unstructured":[80],"format.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"an":[87],"framework":[89,116,131],"for":[90],"that":[95],"takes":[96],"keywords":[97],"based":[98],"queries":[99],"extracts":[102],"most":[104],"using":[111],"text":[112],"mining":[113],"techniques.":[114],"The":[115],"provide":[118],"relevance":[119],"ranking":[120],"given":[125],"query.":[126],"We":[127],"tested":[128],"proposed":[130],"on":[132],"corpus":[133],"at":[136],"GE":[137],"Power":[138],"where":[139],"document":[140],"consists":[141],"more":[143],"than":[144],"hundred":[145],"pages":[146],"in":[147],"PDF.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}