{"id":"https://openalex.org/W2139395348","doi":"https://doi.org/10.1145/2494266.2494319","title":"Recognising document components in XML-based academic articles","display_name":"Recognising document components in XML-based academic articles","publication_year":2013,"publication_date":"2013-09-03","ids":{"openalex":"https://openalex.org/W2139395348","doi":"https://doi.org/10.1145/2494266.2494319","mag":"2139395348"},"language":"en","primary_location":{"id":"doi:10.1145/2494266.2494319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 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/11380/1199172","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":false,"raw_author_name":"Angelo Di Iorio","raw_affiliation_strings":["University of Bologna, Bologna, Italy","University of Bologna , Bologna, Italy"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/A5026721568","display_name":"David M. Shotton","orcid":"https://orcid.org/0000-0001-5506-523X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Shotton","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4605,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96884741,"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":"181","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9962000250816345,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058927059173584},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.7793862819671631},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7365620136260986},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.6664755344390869},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6484054327011108},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5941934585571289},{"id":"https://openalex.org/keywords/well-formed-document","display_name":"Well-formed document","score":0.5173646807670593},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.505155622959137},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.484727144241333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4758974015712738},{"id":"https://openalex.org/keywords/cxml","display_name":"cXML","score":0.474041223526001},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4731672406196594},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4618339538574219},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.43281590938568115},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4158444404602051},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.41330254077911377},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31406310200691223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058927059173584},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.7793862819671631},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7365620136260986},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6664755344390869},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6484054327011108},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5941934585571289},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.5173646807670593},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.505155622959137},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.484727144241333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4758974015712738},{"id":"https://openalex.org/C101509794","wikidata":"https://www.wikidata.org/wiki/Q5014897","display_name":"cXML","level":5,"score":0.474041223526001},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4731672406196594},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4618339538574219},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.43281590938568115},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4158444404602051},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.41330254077911377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31406310200691223},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2494266.2494319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.906.9192","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.906.9192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://speroni.web.cs.unibo.it/publications/di-iorio-2013-recognising-document-components.pdf","raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/392563","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/392563","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:11380/1199172","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1199172","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:11380/1199172","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1199172","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","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W158837568","https://openalex.org/W370717593","https://openalex.org/W852643139","https://openalex.org/W1579225698","https://openalex.org/W1623330217","https://openalex.org/W1977727663","https://openalex.org/W2036242330","https://openalex.org/W2064354603","https://openalex.org/W2097056536","https://openalex.org/W2121911355","https://openalex.org/W2123036199","https://openalex.org/W2151401577","https://openalex.org/W2417295683"],"related_works":["https://openalex.org/W1560643532","https://openalex.org/W881271074","https://openalex.org/W2115081160","https://openalex.org/W2351590241","https://openalex.org/W2051897199","https://openalex.org/W89472578","https://openalex.org/W2181356758","https://openalex.org/W2351083423","https://openalex.org/W1556513644","https://openalex.org/W593963807"],"abstract_inverted_index":{"Recognising":[0],"textual":[1],"structures":[2],"(paragraphs,":[3],"sections,":[4],"etc.)":[5],"provides":[6],"abstract":[7],"and":[8,25],"more":[9],"general":[10],"mechanisms":[11],"for":[12],"describing":[13],"documents":[14],"independent":[15],"of":[16,20,43,49],"the":[17,40],"particular":[18],"semantics":[19],"specific":[21],"markup":[22],"schemas,":[23],"tools":[24],"presentation":[26],"stylesheets.":[27],"In":[28],"this":[29],"paper":[30],"we":[31],"propose":[32],"an":[33],"algorithm":[34],"that":[35],"allows":[36],"us":[37],"to":[38],"identify":[39],"structural":[41],"role":[42],"each":[44],"element":[45],"in":[46],"a":[47],"set":[48],"homogeneous":[50],"scientific":[51],"articles":[52],"stored":[53],"as":[54],"XML":[55],"files.":[56]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
