{"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":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031210","pdf_url":null,"source":null,"license":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5075130969","display_name":"Qiankun Zhao","orcid":null},"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_string":"Nanyang Technological University; Singapore","raw_affiliation_strings":["Nanyang Technological University; Singapore"]},{"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_string":"Nanyang Technological University; Singapore","raw_affiliation_strings":["Nanyang Technological University; Singapore"]},{"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/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_string":"IBM India Research Labs. (India)","raw_affiliation_strings":["IBM India Research Labs. (India)"]},{"author_position":"last","author":{"id":"https://openalex.org/A5039882708","display_name":"Yahiko Kambayashi","orcid":"https://orcid.org/0000-0003-3866-5609"},"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_string":"Kyoto University, Japan","raw_affiliation_strings":["Kyoto University, Japan"]}],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":18,"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Data Stream Management Systems and Techniques","score":0.9986,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Data Stream Management Systems and Techniques","score":0.9986,"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/T10538","display_name":"Data Mining Techniques and Applications","score":0.9965,"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/T11269","display_name":"Text Compression and Indexing Algorithms","score":0.9904,"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"}}],"keywords":[{"keyword":"unordered xml","score":0.5547},{"keyword":"historical structural deltas","score":0.5017},{"keyword":"structures","score":0.3909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724177},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5137099},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.45965594},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4299725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.424868},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3361246},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32452154},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28569067}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031210","pdf_url":null,"source":null,"license":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"referenced_works_count":5,"referenced_works":["https://openalex.org/W1531976089","https://openalex.org/W2030766291","https://openalex.org/W2070046067","https://openalex.org/W2152593687","https://openalex.org/W4252403066"],"related_works":["https://openalex.org/W2378161351","https://openalex.org/W138420226","https://openalex.org/W2115478919","https://openalex.org/W2365827997","https://openalex.org/W2523777935","https://openalex.org/W56234146","https://openalex.org/W1496931240","https://openalex.org/W1501142348","https://openalex.org/W2593656835","https://openalex.org/W4232339987"],"ngrams_url":"https://api.openalex.org/works/W2026168616/ngrams","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],"frequently":[93,136],"changing":[94,137],"structures":[95,138],"from":[96],"sequence":[98],"historical":[100],"structural":[101],"deltas":[102],"unordered":[104],"XML.":[105],"make":[107],"structure":[109],"discovering":[110],"process":[111],"efficient,":[112],"an":[113],"expressive":[114],"compact":[116],"model,":[118,127],"Historical-Document":[119],"Object":[120],"Model":[121],"(H-DOM),":[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]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2026168616","counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2024-03-20T23:09:40.095962","created_date":"2016-06-24"}