{"id":"https://openalex.org/W2171378430","doi":"https://doi.org/10.1109/icdim.2007.4444281","title":"An XML subtree segmentation method based on syntactic segmentation rate","display_name":"An XML subtree segmentation method based on syntactic segmentation rate","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2171378430","doi":"https://doi.org/10.1109/icdim.2007.4444281","mag":"2171378430"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2007.4444281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100544731/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000836998","display_name":"Wenxin Liang","orcid":"https://orcid.org/0000-0002-9166-3138"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wenxin Liang","raw_affiliation_strings":["Japan Science and Technology Agency, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I4210086780","https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077678055","display_name":"Xiangyong Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiangyong Ouyang","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022568434","display_name":"Haruo Yokota","orcid":"https://orcid.org/0000-0001-9788-0443"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruo Yokota","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000836998"],"corresponding_institution_ids":["https://openalex.org/I114531698","https://openalex.org/I4210086780"],"apc_list":null,"apc_paid":null,"fwci":0.6732,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76919865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"551","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.996999979019165,"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":"Advanced Database Systems and Queries","score":0.996999979019165,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9898999929428101,"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/T11106","display_name":"Data Management and Algorithms","score":0.9883999824523926,"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/segmentation","display_name":"Segmentation","score":0.8554121255874634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923257350921631},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6903668642044067},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6480792760848999},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6053847074508667},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.5560252666473389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4500761330127716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3502260446548462},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11488565802574158},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05406329035758972}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8554121255874634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923257350921631},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6903668642044067},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6480792760848999},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6053847074508667},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5560252666473389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4500761330127716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3502260446548462},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11488565802574158},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05406329035758972},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdim.2007.4444281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50007286","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100544731","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100544731/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50007286","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100544731","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100544731/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G12401395","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G4611969921","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G4864544293","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G6267471473","display_name":null,"funder_award_id":"Grant-in-Aid","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G7485138276","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G7599130655","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G7879866177","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8044579487","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171378430.pdf","grobid_xml":"https://content.openalex.org/works/W2171378430.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W123724697","https://openalex.org/W160433801","https://openalex.org/W1576208511","https://openalex.org/W1601158495","https://openalex.org/W1602660880","https://openalex.org/W2040374677","https://openalex.org/W2099630574","https://openalex.org/W2099711139","https://openalex.org/W2109464129","https://openalex.org/W2111087864","https://openalex.org/W2141776324","https://openalex.org/W2164688050","https://openalex.org/W2409915436","https://openalex.org/W4239820202","https://openalex.org/W6634356118","https://openalex.org/W6636140001","https://openalex.org/W6675363005"],"related_works":["https://openalex.org/W2592395359","https://openalex.org/W2045342254","https://openalex.org/W2535231171","https://openalex.org/W1501331687","https://openalex.org/W4255512592","https://openalex.org/W4205247302","https://openalex.org/W2501551404","https://openalex.org/W2326647871","https://openalex.org/W2468652214","https://openalex.org/W1504527458"],"abstract_inverted_index":{"In":[0,30],"this":[1],"paper,":[2],"we":[3,34,97],"propose":[4],"an":[5],"effective":[6,124],"method":[7,59,122],"for":[8,43,125],"segmenting":[9,126],"large":[10],"XML":[11,63,127],"documents":[12,64,128],"into":[13,129],"independent":[14,130],"meaningful":[15,131],"subtrees":[16,81,102,132],"based":[17],"on":[18],"two":[19],"syntactic":[20],"segmentation":[21,24,28,58,121],"rates:":[22],"vertical":[23],"rate":[25],"and":[26,82,91,133,144],"horizontal":[27],"rate.":[29],"the":[31,40,44,52,55,79,85,89,100,118,147],"proposed":[32,56,72,109,119,136],"method,":[33],"use":[35],"DO-VLEI":[36],"code":[37],"to":[38,50,77],"calculate":[39],"required":[41],"parameters":[42],"subtree":[45,57,73,94,110,120,137],"segmentation.":[46],"We":[47,68],"conduct":[48],"experiments":[49],"observe":[51],"effectiveness":[53],"of":[54,93],"using":[60,146],"real":[61],"bibliography":[62],"stored":[65],"in":[66],"RDBs.":[67],"apply":[69],"our":[70,107,134],"previously":[71,108,135],"matching":[74,86,138,142],"algorithm":[75,139],"SLAX":[76,105],"match":[78],"segmented":[80,148],"evaluate":[83],"how":[84],"threshold":[87],"impacts":[88],"precision":[90,143],"recall":[92,145],"matching.":[95],"Besides,":[96],"also":[98],"integrate":[99],"matched":[101],"determined":[103],"by":[104,106],"integration":[111],"algorithm.":[112],"The":[113],"experimental":[114],"results":[115],"indicate":[116],"that":[117],"is":[123],"achieves":[140],"reasonable":[141],"subtrees.":[149]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}