{"id":"https://openalex.org/W2139267689","doi":"https://doi.org/10.1145/1135777.1135965","title":"Using proportional transportation similarity with learned element semantics for XML document clustering","display_name":"Using proportional transportation similarity with learned element semantics for XML document clustering","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2139267689","doi":"https://doi.org/10.1145/1135777.1135965","mag":"2139267689"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5029568096","display_name":"Xiaojun Wan","orcid":"https://orcid.org/0000-0001-6887-1994"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojun Wan","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109205545","display_name":"Jianwu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Yang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029568096"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.954,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75507918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9994000196456909,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711358666419983},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6894932985305786},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6627659797668457},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6392380595207214},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6213418841362},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5997804999351501},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5928779244422913},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.46607494354248047},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4286068081855774},{"id":"https://openalex.org/keywords/xml-framework","display_name":"XML framework","score":0.4175525903701782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24769997596740723},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23099854588508606},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09477376937866211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711358666419983},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6894932985305786},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6627659797668457},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6392380595207214},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6213418841362},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5997804999351501},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5928779244422913},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.46607494354248047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4286068081855774},{"id":"https://openalex.org/C21761406","wikidata":"https://www.wikidata.org/wiki/Q8042330","display_name":"XML framework","level":3,"score":0.4175525903701782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24769997596740723},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23099854588508606},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09477376937866211},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W154511698","https://openalex.org/W1511554697","https://openalex.org/W1575842006","https://openalex.org/W1976373002","https://openalex.org/W2076680677","https://openalex.org/W2611147814"],"related_works":["https://openalex.org/W2047342127","https://openalex.org/W4251156254","https://openalex.org/W5728047","https://openalex.org/W2112528798","https://openalex.org/W1912491515","https://openalex.org/W2355711613","https://openalex.org/W2149437740","https://openalex.org/W2752365879","https://openalex.org/W1586320753","https://openalex.org/W2109384629"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,66],"novel":[4],"approach":[5,25],"to":[6,27,55],"measuring":[7],"XML":[8,18,57],"document":[9,58],"similarity":[10,59,63],"by":[11,60],"taking":[12],"into":[13],"account":[14],"the":[15,23,29,49,62,83,87],"semantics":[16,41],"between":[17],"elements.":[19],"The":[20,39],"motivation":[21],"of":[22,31,70,86],"proposed":[24,54,88],"is":[26,53],"overcome":[28],"problems":[30],"\"under-contribution\u00f6":[32],"and":[33,48,80],"\"over-contribution\u00f6":[34],"existing":[35],"in":[36,44],"previous":[37],"work.":[38],"element":[40],"are":[42,72],"learned":[43],"an":[45],"unsupervised":[46],"way":[47],"Proportional":[50],"Transportation":[51],"Similarity":[52],"evaluate":[56],"modeling":[61],"calculation":[64],"as":[65],"transportation":[67],"problem.":[68],"Experiments":[69],"clustering":[71],"performed":[73],"on":[74],"three":[75],"ACM":[76],"SIGMOD":[77],"data":[78],"sets":[79],"results":[81],"show":[82],"favorable":[84],"performance":[85],"approach.":[89]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}