{"id":"https://openalex.org/W2566828227","doi":"https://doi.org/10.1109/ccis.2016.7790302","title":"Semi-structured document extraction based on document element block model","display_name":"Semi-structured document extraction based on document element block model","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2566828227","doi":"https://doi.org/10.1109/ccis.2016.7790302","mag":"2566828227"},"language":"en","primary_location":{"id":"doi:10.1109/ccis.2016.7790302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2016.7790302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS)","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/A5100715716","display_name":"Tao Lv","orcid":"https://orcid.org/0000-0003-3981-2949"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Lv","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325222","display_name":"Jiang Liu","orcid":"https://orcid.org/0000-0002-0729-1299"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Liu","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080310406","display_name":"Fan L\u00fc","orcid":"https://orcid.org/0000-0002-4932-3850"},"institutions":[{"id":"https://openalex.org/I4210120069","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25","country_code":"CN","type":"funder","lineage":["https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Lu","raw_affiliation_strings":["Ministry of Science and Technology of the People's Republic of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Science and Technology of the People's Republic of China, Beijing, China","institution_ids":["https://openalex.org/I4210120069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364209","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0003-0228-9330"},"institutions":[{"id":"https://openalex.org/I4210120069","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25","country_code":"CN","type":"funder","lineage":["https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Ministry of Science and Technology of the People's Republic of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Science and Technology of the People's Republic of China, Beijing, China","institution_ids":["https://openalex.org/I4210120069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410974","display_name":"Xinyan Wang","orcid":"https://orcid.org/0000-0001-9921-3134"},"institutions":[{"id":"https://openalex.org/I4210141682","display_name":"Air Force General Hospital PLA","ror":"https://ror.org/042jtt364","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210141682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Wang","raw_affiliation_strings":["Air Force General Hospital, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Air Force General Hospital, Beijing, China","institution_ids":["https://openalex.org/I4210141682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101811814","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0002-2504-4056"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100715716"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09379821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"461","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9836000204086304,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9836000204086304,"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/T14025","display_name":"Educational Technology and Assessment","score":0.9186000227928162,"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/T14276","display_name":"Power Systems and Technologies","score":0.9046000242233276,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780978679656982},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6915299296379089},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5980815887451172},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.5897911190986633},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5661717653274536},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5463880896568298},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.5450717210769653},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5331560373306274},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.525601863861084},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.48219695687294006},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.4758955240249634},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4255830943584442},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3873695731163025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25969839096069336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11872372031211853},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.11190176010131836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10239678621292114},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08730477094650269},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07309597730636597},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.07119566202163696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780978679656982},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6915299296379089},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5980815887451172},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.5897911190986633},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5661717653274536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5463880896568298},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.5450717210769653},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5331560373306274},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.525601863861084},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.48219695687294006},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.4758955240249634},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4255830943584442},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3873695731163025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25969839096069336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11872372031211853},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.11190176010131836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10239678621292114},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08730477094650269},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07309597730636597},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.07119566202163696},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis.2016.7790302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2016.7790302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS)","raw_type":"proceedings-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/W176257381","https://openalex.org/W2153072229"],"related_works":["https://openalex.org/W2351590241","https://openalex.org/W2014142435","https://openalex.org/W2352672621","https://openalex.org/W8654319","https://openalex.org/W2374990542","https://openalex.org/W2605223516","https://openalex.org/W2284631983","https://openalex.org/W2051616516","https://openalex.org/W2808460028","https://openalex.org/W2367919820"],"abstract_inverted_index":{"A":[0],"large":[1],"number":[2],"of":[3,49,90,98,101,104],"documents":[4,28,72],"related":[5],"to":[6,110,133,157],"its":[7],"specific":[8],"business":[9],"are":[10],"produced":[11],"continually":[12],"by":[13,116],"enterprises":[14],"and":[15,36,73,76,131,137],"institutions":[16],"in":[17,39,53],"their":[18],"daily":[19],"work.":[20],"To":[21],"get":[22],"useful":[23],"information":[24,51],"from":[25,70],"these":[26],"semi-structured":[27,41,159],"we":[29,151],"have":[30],"proposed":[31],"document":[32,42,67,86,99,107],"element":[33,68,87],"block":[34,69,88,114],"model(DEBM)":[35],"applied":[37],"it":[38],"the":[40,50,54,58,63,85,111,140],"extraction.":[43],"The":[44,120,147],"model":[45,156],"makes":[46],"full":[47],"use":[48],"contains":[52],"document,":[55,92],"not":[56],"only":[57],"structural":[59],"information,":[60],"but":[61],"also":[62],"content.":[64],"DEBM":[65,127,144],"extracts":[66],"template":[71,91,138],"target":[74],"documents,":[75],"then":[77],"generate":[78],"corresponding":[79,112],"regular":[80,117,135],"expression":[81,118],"rules":[82],"based":[83,125,142],"on":[84,126,143],"characteristic":[89],"after":[93],"that":[94,123,150],"process":[95],"each":[96],"type":[97],"elements":[100,108,113],"a":[102,153],"set":[103],"blocks":[105],"extracted":[106],"according":[109],"position":[115],"matching.":[119],"experiments":[121],"show":[122],"extraction":[124],"achieved":[128],"good":[129],"results":[130],"compared":[132],"traditional":[134],"expressions":[136],"matching,":[139],"approach":[141],"performs":[145],"better.":[146],"result":[148],"shows":[149],"propose":[152],"simple,":[154],"efficient":[155],"extract":[158],"documents.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
