{"id":"https://openalex.org/W1873894770","doi":null,"title":"An Ontology for Domain-oriented Semantic Similarity Search on XML Data","display_name":"An Ontology for Domain-oriented Semantic Similarity Search on XML Data","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1873894770","mag":"1873894770"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.4431","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.4431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://domino.mpi-inf.mpg.de/intranet/ag5/ag5publ.nsf/80255f02006a559a80255ef20056fc02/ac3e0008192bbd18c1256de90054a8c6/$file/theobald_btw2003.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5033179738","display_name":"Anja Theobald","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Theobald, Anja","raw_affiliation_strings":["Databases and Information Systems, MPI for Informatics, Max Planck Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databases and Information Systems, MPI for Informatics, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098","observed_orcids":["https://orcid.org/0000-0003-4959-6098","https://orcid.org/0000-0002-6264-6822"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Weikum, Gerhard","raw_affiliation_strings":["Databases and Information Systems, MPI for Informatics, Max Planck Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Databases and Information Systems, MPI for Informatics, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042236085","display_name":"Harald Sch\u00f6ning","orcid":"https://orcid.org/0000-0002-4480-8269","observed_orcids":["https://orcid.org/0000-0002-4480-8269"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sch\u00f6ning, Harald","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075756237","display_name":"Erhard Rahm","orcid":"https://orcid.org/0000-0002-2665-1114","observed_orcids":["https://orcid.org/0000-0002-2665-1114"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahm, Erhard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6106,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69621709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8281000256538391,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8281000256538391,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.10040000081062317,"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":0.053300000727176666,"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/semantic-similarity-search","display_name":"semantic similarity search","score":0.9739999771118164},{"id":"https://openalex.org/keywords/xml-data","display_name":"XML data","score":0.8980000019073486},{"id":"https://openalex.org/keywords/domain-specific-search","display_name":"domain-specific search","score":0.6909999847412109},{"id":"https://openalex.org/keywords/relevance-measures","display_name":"relevance measures","score":0.3970000147819519},{"id":"https://openalex.org/keywords/search-engines","display_name":"search engines","score":0.6919999718666077},{"id":"https://openalex.org/keywords/xml-document-structure","display_name":"XML document structure","score":0.46000000834465027},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.36500000953674316},{"id":"https://openalex.org/keywords/xquery","display_name":"XQuery","score":0.8399999737739563},{"id":"https://openalex.org/keywords/boolean-retrieval","display_name":"Boolean retrieval","score":0.7559999823570251},{"id":"https://openalex.org/keywords/ranked-retrieval","display_name":"ranked retrieval","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8265902996063232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956576347351074},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.7329680919647217},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4894975423812866},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.48588865995407104},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.44946083426475525},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4189620018005371},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3238585591316223},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24698075652122498},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.23255223035812378},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.21599829196929932}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.4431","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.4431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://domino.mpi-inf.mpg.de/intranet/ag5/ag5publ.nsf/80255f02006a559a80255ef20056fc02/ac3e0008192bbd18c1256de90054a8c6/$file/theobald_btw2003.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:202245","doi":null,"is_oa":false,"landing_page_url":"http://edoc.mpg.de/202245","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW) : 10. GI-Fachtagung, Bonner K\u00f6llen, 217-226 (2003)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1329973","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-2C2C-E","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lecture Notes in Informatics","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W11295630","https://openalex.org/W657079967","https://openalex.org/W1504993955","https://openalex.org/W1525986373","https://openalex.org/W1530737162","https://openalex.org/W1538246304","https://openalex.org/W1555057198","https://openalex.org/W1577372497","https://openalex.org/W1604803281","https://openalex.org/W1660390307","https://openalex.org/W2013848664","https://openalex.org/W2023263708","https://openalex.org/W2038721957","https://openalex.org/W2040108765","https://openalex.org/W2075043418","https://openalex.org/W2122410182","https://openalex.org/W2126557644","https://openalex.org/W2133109597","https://openalex.org/W2133959199","https://openalex.org/W2139528831","https://openalex.org/W2479174951","https://openalex.org/W2484652480"],"related_works":["https://openalex.org/W2162988200","https://openalex.org/W2126288128","https://openalex.org/W2402803222","https://openalex.org/W7095249273","https://openalex.org/W7012949286","https://openalex.org/W1538246304","https://openalex.org/W2350360097","https://openalex.org/W1519310261","https://openalex.org/W7100291678","https://openalex.org/W1491797149"],"abstract_inverted_index":{"Query":[0],"languages":[1],"for":[2,97,127],"XML":[3,22,64,102],"such":[4],"as":[5],"XPath":[6],"or":[7,24],"XQuery":[8],"support":[9],"Boolean":[10],"retrieval":[11,47],"where":[12],"\\na":[13],"query":[14,132],"result":[15],"is":[16],"a":[17,113,124],"(possibly":[18],"restructured)":[19],"subset":[20],"of":[21,32,63,131],"elements":[23],"entire":[25],"\\ndocuments":[26],"that":[27],"satisfy":[28],"the":[29,33,39,45,53,61,106],"search":[30,36,72,87,100,122],"conditions":[31],"query.":[34],"Web":[35],"engines,":[37],"\\non":[38],"other":[40],"hand,":[41],"are":[42,80],"based":[43],"on":[44,101],"ranked":[46],"paradigm,":[48],"but":[49],"do":[50],"not":[51],"\\nconsider":[52],"additional":[54],"information":[55],"and":[56,66,79,91],"rich":[57],"annotations":[58],"provided":[59],"by":[60],"\\nstructure":[62],"documents":[65],"their":[67],"element":[68],"names.":[69],"Furthermore,":[70],"web":[71],"\\nengines":[73],"have":[74],"very":[75],"lit-tle":[76],"\u201csemantic\u201d":[77],"data":[78,103],"thus":[81],"unable":[82],"to":[83],"cope":[84],"with":[85,123],"\\nambiguous":[86],"terms.":[88],"Onto-logical":[89],"knowledge":[90],"appropriate":[92],"index":[93,116],"structures":[94],"\\nare":[95],"necessary":[96],"semantic":[98,120],"simi-larity":[99],"extracted":[104],"from":[105],"\\nweb.":[107],"In":[108],"this":[109],"paper":[110],"we":[111],"present":[112],"power-ful":[114],"ontology":[115],"which":[117],"supports":[118],"\\ndomain-specific":[119],"similarity":[121],"new":[125],"measure":[126],"expressing":[128],"\\nthe":[129],"relevance":[130],"results.":[133]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}