{"id":"https://openalex.org/W130971823","doi":"https://doi.org/10.4018/978-1-59904-162-9.ch009","title":"Mining XML Documents","display_name":"Mining XML Documents","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W130971823","doi":"https://doi.org/10.4018/978-1-59904-162-9.ch009","mag":"130971823"},"language":"en","primary_location":{"id":"doi:10.4018/978-1-59904-162-9.ch009","doi":"https://doi.org/10.4018/978-1-59904-162-9.ch009","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-59904-162-9.ch009","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining Patterns","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4246554849","display_name":"Data Mining Patterns"},"type":"book-chapter","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00188899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040379724","display_name":"Laurent Candillier","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Candillier","raw_affiliation_strings":["Universit\u00e9 Charles de Gaulle, France","Groupe de Recherche en Apprentissage Automatique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Charles de Gaulle, France","institution_ids":[]},{"raw_affiliation_string":"Groupe de Recherche en Apprentissage Automatique","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027101473","display_name":"Ludovic Denoyer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405264447","display_name":"Universit\u00e9 Pierre-et-Marie-Curie","ror":"https://ror.org/01yvrd251","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081","https://openalex.org/I4405264447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, France","Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, France","institution_ids":["https://openalex.org/I4405264447"]},{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113667126","display_name":"Patrick Gallinari","orcid":"https://orcid.org/0000-0001-9060-9001","observed_orcids":["https://orcid.org/0000-0001-9060-9001"]},"institutions":[{"id":"https://openalex.org/I4405264447","display_name":"Universit\u00e9 Pierre-et-Marie-Curie","ror":"https://ror.org/01yvrd251","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081","https://openalex.org/I4405264447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, France","Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, France","institution_ids":["https://openalex.org/I4405264447"]},{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108106139","display_name":"Marie-Christine Rousset","orcid":"https://orcid.org/0009-0009-9127-9521","observed_orcids":["https://orcid.org/0009-0009-9127-9521"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie Christine Rousset","raw_affiliation_strings":["LSR-IMAG, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LSR-IMAG, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107414260","display_name":"Alexandre Termier","orcid":"https://orcid.org/0000-0003-1784-0017","observed_orcids":["https://orcid.org/0000-0003-1784-0017"]},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Alexandre Termier","raw_affiliation_strings":["Institute of Statistical Mathematics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Statistical Mathematics, Japan","institution_ids":["https://openalex.org/I4210134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069307808","display_name":"Anne-Marie Vercoustre","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anne-Marie Vercoustre","raw_affiliation_strings":["INRIA, France","INRIA Rocquencourt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Rocquencourt","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5437,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.92656844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.7782999873161316,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.7782999873161316,"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":0.20569999516010284,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.005900000222027302,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294459581375122},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6757202744483948},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.668694794178009},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6138201951980591},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.5850446224212646},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.576499342918396},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5432809591293335},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5338799953460693},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4873424470424652},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.48274511098861694},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4724586009979248},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.4633138179779053},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.4393247067928314},{"id":"https://openalex.org/C21761406","wikidata":"https://www.wikidata.org/wiki/Q8042330","display_name":"XML framework","level":3,"score":0.43924179673194885},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42451798915863037},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.4230746030807495},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34677284955978394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13483017683029175},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.4018/978-1-59904-162-9.ch009","doi":"https://doi.org/10.4018/978-1-59904-162-9.ch009","is_oa":false,"landing_page_url":"https://doi.org/10.4018/978-1-59904-162-9.ch009","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining Patterns","raw_type":"book-chapter"},{"id":"doi:10.4018/9781599041629.ch009","doi":"https://doi.org/10.4018/9781599041629.ch009","is_oa":false,"landing_page_url":"https://doi.org/10.4018/9781599041629.ch009","pdf_url":null,"source":{"id":"https://openalex.org/S4306463409","display_name":"IGI Global eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining Patterns","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.7119","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.7119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/18/88/99/PDF/XML-MiningChapter_final.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00188899v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00188899","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"P. Poncelet, F. Masseglia, M. Teisseire. Data Mining Patterns: New Methods and Applications, Information Science Reference, pp.198-219, 2007, ⟨10.4018/978-1-59904-162-9.ch009⟩","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00188899v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00188899","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"P. Poncelet, F. Masseglia, M. Teisseire. Data Mining Patterns: New Methods and Applications, Information Science Reference, pp.198-219, 2007, ⟨10.4018/978-1-59904-162-9.ch009⟩","raw_type":"info:eu-repo/semantics/bookPart"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W56896489","https://openalex.org/W118635492","https://openalex.org/W129383413","https://openalex.org/W154511698","https://openalex.org/W1121883017","https://openalex.org/W1506285740","https://openalex.org/W1515905426","https://openalex.org/W1520566981","https://openalex.org/W1544892355","https://openalex.org/W1574284628","https://openalex.org/W1586500735","https://openalex.org/W1592758009","https://openalex.org/W1602595918","https://openalex.org/W1628571627","https://openalex.org/W1641749581","https://openalex.org/W1970881376","https://openalex.org/W1976373002","https://openalex.org/W2070046067","https://openalex.org/W2070571200","https://openalex.org/W2103069411","https://openalex.org/W2106206965","https://openalex.org/W2107922666","https://openalex.org/W2113854849","https://openalex.org/W2122303450","https://openalex.org/W2134222424","https://openalex.org/W2135850471","https://openalex.org/W2138370341","https://openalex.org/W2139081439","https://openalex.org/W2143774317","https://openalex.org/W2517878783","https://openalex.org/W4239110525"],"related_works":["https://openalex.org/W2387983968","https://openalex.org/W2107922666","https://openalex.org/W2786168723","https://openalex.org/W7062237149","https://openalex.org/W1979920329","https://openalex.org/W150236139","https://openalex.org/W1547583365","https://openalex.org/W2139081439","https://openalex.org/W1533862678","https://openalex.org/W2387745803"],"abstract_inverted_index":{"XML":[0,26,57,60,143],"documents":[1,61,89],"are":[2,68,105],"becoming":[3],"ubiquitous":[4],"because":[5],"of":[6,19,25,56,80,111,141],"their":[7],"rich":[8],"and":[9,45,82,90,102,128],"flexible":[10],"format":[11],"that":[12,33],"can":[13,62],"be":[14,43,49,63,72],"used":[15],"for":[16,36,107,119],"a":[17,139],"variety":[18,140],"applications.":[20],"Giving":[21],"the":[22,53],"increasing":[23],"size":[24],"collections":[27,38],"as":[28,65],"information":[29],"sources,":[30],"mining":[31,93,99],"techniques":[32],"traditionally":[34],"exist":[35],"text":[37,108],"or":[39],"databases":[40],"need":[41],"to":[42,48,51,71,87,130,149],"adapted":[44],"new":[46],"methods":[47],"invented":[50],"exploit":[52],"particular":[54],"structure":[55,86,114],"documents.":[58],"Basically":[59],"seen":[64],"trees,":[66],"which":[67,104,115],"well":[69],"known":[70],"complex":[73],"structures.":[74],"This":[75,122],"chapter":[76,123],"describes":[77],"various":[78],"ways":[79],"using":[81],"simplifying":[83],"this":[84,151],"tree":[85,113],"model":[88],"support":[91,131],"efficient":[92],"algorithms.":[94],"We":[95],"focus":[96],"on":[97,138],"three":[98],"tasks:":[100],"classification":[101],"clustering":[103],"standard":[106],"collections;":[109],"discovering":[110],"frequent":[112],"is":[116],"especially":[117],"important":[118],"heterogeneous":[120],"collection.":[121],"presents":[124],"some":[125],"recent":[126],"approaches":[127],"algorithms":[129],"these":[132],"tasks":[133],"together":[134],"with":[135],"experimental":[136],"evaluation":[137],"large":[142],"collections.Request":[144],"access":[145],"from":[146],"your":[147],"librarian":[148],"read":[150],"chapter's":[152],"full":[153],"text.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}