{"id":"https://openalex.org/W2062521416","doi":"https://doi.org/10.1109/bmei.2012.6513057","title":"Efficient schema extraction from large XML documents","display_name":"Efficient schema extraction from large XML documents","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2062521416","doi":"https://doi.org/10.1109/bmei.2012.6513057","mag":"2062521416"},"language":"en","primary_location":{"id":"doi:10.1109/bmei.2012.6513057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmei.2012.6513057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 5th International Conference on BioMedical Engineering and Informatics","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/A5100343712","display_name":"Yin Zhang\u22c6","orcid":"https://orcid.org/0000-0002-1772-0763"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101446779","display_name":"Hua Zhou","orcid":"https://orcid.org/0000-0001-9381-0827"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhou","raw_affiliation_strings":["School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640523","display_name":"Junhui Liu","orcid":"https://orcid.org/0000-0002-7600-1670"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Liu","raw_affiliation_strings":["School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454824","display_name":"Zhihong Liang","orcid":"https://orcid.org/0000-0001-8118-753X"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Liang","raw_affiliation_strings":["School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Yunnan University; Key Laboratory of Software Engineering of Yunnan Province Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"Key Lab. of Software Eng. of Yunnan Province, Yunnan Univ., Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032476736","display_name":"Peng Duan","orcid":"https://orcid.org/0000-0001-8007-2052"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Duan","raw_affiliation_strings":["Network and Information Center, Yunnan University, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Network and Information Center, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100343712"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15924682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1255","last_page":"1260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.998199999332428,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8555607795715332},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.8204177618026733},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.6495330333709717},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6311352849006653},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5735858082771301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5654032826423645},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5422791242599487},{"id":"https://openalex.org/keywords/relax-ng","display_name":"RELAX NG","score":0.5383272171020508},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5134781002998352},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.41271692514419556},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.3631485104560852},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3525097370147705},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3221599757671356},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15488052368164062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555607795715332},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.8204177618026733},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.6495330333709717},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6311352849006653},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5735858082771301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5654032826423645},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5422791242599487},{"id":"https://openalex.org/C44540991","wikidata":"https://www.wikidata.org/wiki/Q1314117","display_name":"RELAX NG","level":5,"score":0.5383272171020508},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5134781002998352},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.41271692514419556},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3631485104560852},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3525097370147705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3221599757671356},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15488052368164062}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bmei.2012.6513057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmei.2012.6513057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 5th International Conference on BioMedical Engineering and Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1482220696","https://openalex.org/W2057185776","https://openalex.org/W2089634871","https://openalex.org/W2137692226","https://openalex.org/W2154475850","https://openalex.org/W4206680187"],"related_works":["https://openalex.org/W1529503031","https://openalex.org/W2014142435","https://openalex.org/W1592776645","https://openalex.org/W1579700978","https://openalex.org/W2102900423","https://openalex.org/W2482975607","https://openalex.org/W1563174341","https://openalex.org/W1501264070","https://openalex.org/W2131299923","https://openalex.org/W49747556"],"abstract_inverted_index":{"Although":[0],"the":[1,71,91,109,117],"presence":[2],"of":[3,41,58,99],"a":[4,29,34,84,95,147,163],"schema":[5,154],"enables":[6],"many":[7,19,80],"optimizations":[8],"for":[9,155],"operations":[10],"on":[11,70,74],"XML":[12,20,53,100],"documents,":[13],"several":[14,122],"studies":[15],"have":[16],"shown":[17],"that":[18,49,88],"documents":[21,101,132],"in":[22,64,137],"practice":[23],"either":[24],"do":[25],"not":[26],"refer":[27,32],"to":[28,33,44,115,129,145],"schema,":[30],"or":[31,165],"syntactically":[35],"incorrect":[36],"one.":[37],"It":[38],"is":[39,102,143],"therefore":[40],"utmost":[42],"importance":[43],"provide":[45,83],"tools":[46],"and":[47,112,139,152,171],"techniques":[48],"can":[50],"automatically":[51],"generate":[52],"Schema":[54],"Definitions":[55],"from":[56],"sets":[57],"sample":[59],"documents.":[60],"While":[61],"previous":[62],"work":[63],"this":[65],"area":[66],"has":[67],"mostly":[68],"focused":[69],"method":[72],"based":[73],"regular":[75],"expressions,":[76],"we":[77],"consider":[78],"its":[79],"inadequacies.":[81],"We":[82],"theoretically":[85],"complete":[86],"algorithm":[87],"always":[89],"infers":[90],"correct":[92],"XSDs":[93],"when":[94],"sufficiently":[96],"large":[97,131],"corpus":[98],"available.":[103],"In":[104],"addition,":[105],"XTree":[106,127],"impressively":[107],"minimizes":[108],"necessary":[110],"time":[111,138],"main":[113],"memory":[114,140],"extract":[116,146],"schema.":[118],"Our":[119],"approach":[120],"features":[121,170],"advantages":[123],"over":[124],"known":[125],"techniques:":[126],"scales":[128],"very":[130],"(beyond":[133],"1":[134],"GB)":[135],"both":[136],"consumption;":[141],"it":[142,158],"able":[144],"general,":[148],"complete,":[149],"correct,":[150],"minimal,":[151],"readable":[153],"complex":[156],"documents;":[157],"detects":[159],"elements":[160],"appear":[161],"as":[162],"sequence":[164],"choice.":[166],"Experiments":[167],"confirm":[168],"these":[169],"properties.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}