{"id":"https://openalex.org/W1977727663","doi":"https://doi.org/10.1145/2361354.2361374","title":"A first approach to the automatic recognition of structural patterns in XML documents","display_name":"A first approach to the automatic recognition of structural patterns in XML documents","publication_year":2012,"publication_date":"2012-09-04","ids":{"openalex":"https://openalex.org/W1977727663","doi":"https://doi.org/10.1145/2361354.2361374","mag":"1977727663"},"language":"en","primary_location":{"id":"doi:10.1145/2361354.2361374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11380/1199166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027086183","display_name":"Angelo Di Iorio","orcid":"https://orcid.org/0000-0002-6893-7452"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Angelo Di Iorio","raw_affiliation_strings":["University of Bologna, Bologna, Italy","University of Bologna , Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna , Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031461768","display_name":"Silvio Peroni","orcid":"https://orcid.org/0000-0003-0530-4305"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvio Peroni","raw_affiliation_strings":["University of Bologna, Bologna, Italy","University of Bologna , Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna , Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022499156","display_name":"Francesco Poggi","orcid":"https://orcid.org/0000-0001-6577-5606"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Poggi","raw_affiliation_strings":["University of Bologna, Bologna, Italy","University of Bologna , Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna , Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029129300","display_name":"Fabio Vitali","orcid":"https://orcid.org/0000-0002-7562-5203"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Vitali","raw_affiliation_strings":["University of Bologna, Bologna, Italy","University of Bologna , Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna , Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027086183"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":6.586,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96228462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9972000122070312,"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":0.9955999851226807,"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":0.8557924032211304},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.650049090385437},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6331006288528442},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.632920503616333},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5477199554443359},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4790683686733246},{"id":"https://openalex.org/keywords/conceptualization","display_name":"Conceptualization","score":0.43193119764328003},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.4238066077232361},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.42175230383872986},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.42041856050491333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42000848054885864},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41073551774024963},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19171488285064697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13124486804008484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557924032211304},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.650049090385437},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6331006288528442},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.632920503616333},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5477199554443359},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4790683686733246},{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.43193119764328003},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.4238066077232361},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.42175230383872986},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.42041856050491333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42000848054885864},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41073551774024963},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19171488285064697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13124486804008484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2361354.2361374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.460.4300","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.460.4300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://palindrom.es/phd/wp-content/uploads/2010/07/dcng18-diiorio.pdf","raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/123083","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/123083","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unimore.it:11380/1199166","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1199166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1199166","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1199166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W370717593","https://openalex.org/W1542417898","https://openalex.org/W1573733520","https://openalex.org/W1649645444","https://openalex.org/W1752569088","https://openalex.org/W1794411284","https://openalex.org/W1975700640","https://openalex.org/W2056065233","https://openalex.org/W2065319396","https://openalex.org/W2077680785","https://openalex.org/W2082889466","https://openalex.org/W2121506769","https://openalex.org/W2144245782","https://openalex.org/W2150617113","https://openalex.org/W3116423790","https://openalex.org/W3146347964","https://openalex.org/W4237592749","https://openalex.org/W4285719527","https://openalex.org/W6681963627"],"related_works":["https://openalex.org/W2084734328","https://openalex.org/W2093226355","https://openalex.org/W12825674","https://openalex.org/W2198920752","https://openalex.org/W2015791292","https://openalex.org/W4235145451","https://openalex.org/W2044641582","https://openalex.org/W4232022739","https://openalex.org/W2076638146","https://openalex.org/W2808460028"],"abstract_inverted_index":{"XML":[0],"is":[1],"among":[2],"the":[3,8,46,70,72,92,125,174],"preferred":[4],"formats":[5],"for":[6],"storing":[7],"structure":[9],"of":[10,49,57,91,105,124,127,151,176,182],"documents":[11,107,122],"such":[12,28,97,152],"as":[13,29],"scientific":[14],"articles,":[15],"manuals,":[16],"documentation,":[17],"literary":[18],"works,":[19],"etc.":[20],"Sometimes":[21],"publishers":[22],"adopt":[23],"established":[24],"and":[25,31,54,80,82,87,115,131,154],"well-known":[26],"vocabularies":[27,61,79],"DocBook":[30],"TEI,":[32],"other":[33],"times":[34],"they":[35,156],"create":[36],"partially":[37],"or":[38],"entirely":[39],"new":[40],"ones":[41],"that":[42,76,83,169],"better":[43,103],"deal":[44],"with":[45],"particular":[47],"requirements":[48,56],"their":[50],"documents.":[51,163,185],"The":[52],"(explicit":[53],"implicit)":[55],"use":[58],"in":[59,179],"these":[60],"often":[62],"follow":[63],"well-established":[64],"patterns,":[65],"creating":[66],"meta-structures":[67,98],"(the":[68],"block,":[69],"container,":[71],"inline":[73],"element,":[74],"etc.)":[75],"persist":[77],"across":[78],"authors":[81],"describe":[84],"a":[85,102,139,149,180],"truer":[86],"more":[88,116],"general":[89,117],"conceptualization":[90],"documents'":[93],"building":[94],"blocks.":[95],"Addressing":[96],"not":[99],"only":[100],"gives":[101],"insight":[104],"what":[106],"really":[108],"are":[109],"composed":[110],"of,":[111],"but":[112],"provides":[113],"abstract":[114],"mechanisms":[118],"to":[119,172],"work":[120],"on":[121,143],"regardless":[123],"availability":[126],"specific":[128],"schemas,":[129],"tools":[130],"presentation":[132],"stylesheets.":[133],"In":[134],"this":[135],"paper":[136],"we":[137,165],"introduce":[138],"schemaindependent":[140],"theory":[141],"based":[142],"eleven":[144],"structural":[145],"patterns.":[146],"We":[147],"provide":[148],"definition":[150],"patterns":[153],"how":[155],"synthesize":[157],"characteristics":[158],"emerging":[159],"from":[160],"real":[161],"markup":[162,184],"Additionally,":[164],"propose":[166],"an":[167],"algorithm":[168],"allows":[170],"us":[171],"identify":[173],"pattern":[175],"each":[177],"element":[178],"set":[181],"homogeneous":[183]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
