{"id":"https://openalex.org/W2026168616","doi":"https://doi.org/10.1145/1031171.1031210","title":"Discovering frequently changing structures from historical structural deltas of unordered XML","display_name":"Discovering frequently changing structures from historical structural deltas of unordered XML","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W2026168616","doi":"https://doi.org/10.1145/1031171.1031210","mag":"2026168616"},"language":"en","primary_location":{"id":"doi:10.1145/1031171.1031210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075130969","display_name":"Qiankun Zhao","orcid":"https://orcid.org/0000-0001-7804-0430"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiankun Zhao","raw_affiliation_strings":["Nanyang Technological University, Singapore","Nanyang Technological University (Singapore)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University (Singapore)","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061002947","display_name":"Sourav S. Bhowmick","orcid":"https://orcid.org/0000-0003-1957-8016"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sourav S. Bhowmick","raw_affiliation_strings":["Nanyang Technological University, Singapore","Nanyang Technological University (Singapore)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University (Singapore)","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_strings":["IBM India Research Lab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103702858","display_name":"Yahiko Kambayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yahiko Kambayashi","raw_affiliation_strings":["Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9979000091552734,"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/T11106","display_name":"Data Management and Algorithms","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7799654006958008},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.6261402368545532},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.6031970381736755},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.6007623672485352},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.5884575247764587},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5602512359619141},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.546822726726532},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49112269282341003},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4607895314693451},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4555957317352295},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.4536121189594269},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.442204087972641},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3368140459060669},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2871095538139343},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.159121572971344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799654006958008},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.6261402368545532},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.6031970381736755},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.6007623672485352},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.5884575247764587},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5602512359619141},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.546822726726532},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49112269282341003},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4607895314693451},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4555957317352295},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.4536121189594269},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.442204087972641},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3368140459060669},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2871095538139343},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.159121572971344}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1031171.1031210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.7411","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cais.ntu.edu.sg/~qkzhao/pdf/CIKM04Zhao.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cs.dal.ca/~eem/malnis/Readings/CIKM2004/docs/p188.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1531976089","https://openalex.org/W1552413647","https://openalex.org/W1641749581","https://openalex.org/W2030766291","https://openalex.org/W2064853889","https://openalex.org/W2070046067","https://openalex.org/W2136393336","https://openalex.org/W2136593687","https://openalex.org/W2152593687","https://openalex.org/W2161974882","https://openalex.org/W2170726034","https://openalex.org/W4252403066"],"related_works":["https://openalex.org/W2378161351","https://openalex.org/W56234146","https://openalex.org/W2401139123","https://openalex.org/W2154945712","https://openalex.org/W2103912919","https://openalex.org/W2076199141","https://openalex.org/W2536894089","https://openalex.org/W2357844625","https://openalex.org/W2106024890","https://openalex.org/W1975413421"],"abstract_inverted_index":{"Recently,":[0],"a":[1,87],"large":[2],"amount":[3],"of":[4,18,39,43,51,55,99,103,143],"work":[5],"has":[6,47],"been":[7],"done":[8],"in":[9,33,66],"XML":[10,26,29,58,71,74,145],"data":[11,30,117],"mining.":[12],"However,":[13],"we":[14,85],"observed":[15],"that":[16,152],"most":[17],"the":[19,24,37,44,49,53,92,97,108,135,144,157],"existing":[20,45],"works":[21,46],"focus":[22],"on":[23],"snapshot":[25],"data,":[27],"while":[28],"is":[31,123],"dynamic":[32],"real":[34],"applications.":[35],"To":[36,106],"best":[38],"our":[40,153],"knowledge,":[41],"none":[42],"addressed":[48],"issue":[50],"mining":[52,61],"history":[54],"changes":[56],"to":[57,90],"documents.":[59],"Such":[60],"results":[62,150],"can":[63,132],"be":[64],"useful":[65],"many":[67],"applications":[68],"such":[69],"as":[70],"change":[72],"detection,":[73],"indexing,":[75],"association":[76],"rule":[77],"mining,":[78],"and":[79,115,162],"classification":[80],"etc.":[81],"In":[82],"this":[83,126],"paper,":[84],"propose":[86],"novel":[88],"approach":[89],"discover":[91,133],"<i>frequently":[93,136],"changing":[94,137],"structures</i>":[95,138],"from":[96],"sequence":[98],"historical":[100],"<i>structural":[101],"deltas</i>":[102],"unordered":[104],"XML.":[105],"make":[107],"structure":[109],"discovering":[110],"process":[111],"efficient,":[112],"an":[113],"expressive":[114],"compact":[116],"model,":[118,127],"<b>H</b>istorical-<b>D</b>ocument":[119],"<b>O</b>bject":[120],"<b>M</b>odel":[121],"(<b>H-DOM</b>),":[122],"proposed.":[124],"Using":[125],"two":[128,141],"basic":[129],"algorithms,":[130,154],"which":[131],"all":[134],"with":[139,156],"only":[140],"scans":[142],"sequence,":[146],"are":[147,160],"presented.":[148],"Experimental":[149],"show":[151],"together":[155],"optimization":[158],"techniques,":[159],"efficient":[161],"scalable.":[163]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
