{"id":"https://openalex.org/W2157481857","doi":"https://doi.org/10.1145/253260.253406","title":"Structural matching and discovery in document databases","display_name":"Structural matching and discovery in document databases","publication_year":1997,"publication_date":"1997-01-01","ids":{"openalex":"https://openalex.org/W2157481857","doi":"https://doi.org/10.1145/253260.253406","mag":"2157481857"},"language":"en","primary_location":{"id":"doi:10.1145/253260.253406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/253260.253406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1997 ACM SIGMOD international conference on Management of data  - SIGMOD '97","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/A5067937907","display_name":"Jason Tsong-Li Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Tsong-Li Wang","raw_affiliation_strings":["Computer and Information Science, New Jersey Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Computer and Information Science, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055576104","display_name":"Dennis Shasha","orcid":"https://orcid.org/0000-0002-7036-3312"},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Shasha","raw_affiliation_strings":["Courant Institute, New York University"],"affiliations":[{"raw_affiliation_string":"Courant Institute, New York University","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110885744","display_name":"George Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George J. S. Chang","raw_affiliation_strings":["Computer and Information Science, New Jersey Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Computer and Information Science, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032642929","display_name":"Liam Relihan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liam Relihan","raw_affiliation_strings":["Piercom Ltd., Inter. Business Center, National Tech. Park, Limerick, Ireland"],"affiliations":[{"raw_affiliation_string":"Piercom Ltd., Inter. Business Center, National Tech. Park, Limerick, Ireland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081729547","display_name":"Kaizhong Zhang","orcid":"https://orcid.org/0000-0003-1734-5921"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kaizhong Zhang","raw_affiliation_strings":["Computer Science Department, Univ. of Western Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Univ. of Western Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111900926","display_name":"Girish Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Girish Patel","raw_affiliation_strings":["Computer and Information Science, New Jersey Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Computer and Information Science, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067937907"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":4.823,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95485365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"560","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8882988691329956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.699966311454773},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.6862565279006958},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.6534003615379333},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5608561635017395},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.5007338523864746},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49166709184646606},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.48867014050483704},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4682425260543823},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.41654354333877563},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41381022334098816},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4034488797187805},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.3991154730319977},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.39187607169151306},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.23008990287780762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882988691329956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.699966311454773},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.6862565279006958},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.6534003615379333},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5608561635017395},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.5007338523864746},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49166709184646606},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.48867014050483704},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4682425260543823},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.41654354333877563},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41381022334098816},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4034488797187805},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.3991154730319977},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.39187607169151306},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.23008990287780762},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/253260.253406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/253260.253406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1997 ACM SIGMOD international conference on Management of data  - SIGMOD '97","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.4668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.4668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccsweb.njit.edu/~jason/publications/ARTICLES/sigmod1997.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W81892448","https://openalex.org/W117689219","https://openalex.org/W1494307597","https://openalex.org/W1971845537","https://openalex.org/W1976373002","https://openalex.org/W2024797550","https://openalex.org/W2035582095","https://openalex.org/W2054406292","https://openalex.org/W2140713336","https://openalex.org/W2145805921","https://openalex.org/W2147752879","https://openalex.org/W2163569347","https://openalex.org/W2166667085","https://openalex.org/W3146706731","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2182127031","https://openalex.org/W2808460028","https://openalex.org/W4255056669","https://openalex.org/W1552337495","https://openalex.org/W4243796650","https://openalex.org/W2911311438","https://openalex.org/W1973082075","https://openalex.org/W2497533094","https://openalex.org/W4243434273","https://openalex.org/W2059388439"],"abstract_inverted_index":{"Structural":[0],"matching":[1,71,189],"and":[2,9,26,61,127,143,184],"discovery":[3,106],"in":[4,42,45,77,89,97,172],"documents":[5,101,126,138,181],"such":[6],"as":[7,69,104,139],"SGML":[8],"HTML":[10,47],"is":[11,177],"important":[12],"for":[13,122],"data":[14],"warehousing":[15],"[6],":[16],"version":[17,63],"management":[18],"[7,":[19],"11],":[20],"hypertext":[21,78],"authoring,":[22,79],"digital":[23],"libraries":[24],"[4]":[25],"Internet":[27],"databases.":[28],"As":[29,74],"an":[30,46,145,164],"example,":[31,76],"a":[32,80,94,98,116,170],"user":[33,81],"of":[34,64,72,93,100,107,148,169],"the":[35,59,65,86,90,134,137,157,173],"World":[36],"Wide":[37],"Web":[38],"may":[39,82],"be":[40,55,163],"interested":[41],"knowing":[43],"changes":[44,53],"document":[48,66,95,154],"[2,":[49],"5,":[50],"10].":[51],"Such":[52],"can":[54],"detected":[56],"by":[57],"comparing":[58,123],"old":[60],"new":[62],"(referred":[67,102],"to":[68,84,103,151,156],"structural":[70,105],"documents).":[73,108],"another":[75],"wish":[83],"find":[85],"common":[87],"portions":[88],"history":[91],"list":[92],"or":[96,167],"database":[99],"In":[109],"SIGMOD":[110],"95":[111],"demo":[112],"sessions,":[113],"we":[114],"exhibited":[115],"software":[117],"package,":[118],"called":[119],"TreeDiff":[120],"[13],":[121],"two":[124,132],"latex":[125],"showing":[128],"their":[129],"differences.":[130],"Given":[131],"documents,":[133],"tool":[135,176],"represents":[136],"ordered":[140],"labeled":[141],"trees":[142],"finds":[144],"optimal":[146],"sequence":[147],"edit":[149,160],"operations":[150],"transform":[152],"one":[153],"(tree)":[155],"other.":[158],"An":[159],"operation":[161],"could":[162],"insert,":[165],"delete,":[166],"change":[168],"node":[171],"trees.":[174],"The":[175],"so":[178],"named":[179],"because":[180],"are":[182],"represented":[183],"compared":[185],"using":[186],"approximate":[187],"tree":[188],"techniques":[190],"[9,":[191],"12,":[192],"14].":[193]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
