{"id":"https://openalex.org/W2043795882","doi":"https://doi.org/10.14778/2536360.2536361","title":"On repairing structural problems in semi-structured data","display_name":"On repairing structural problems in semi-structured data","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2043795882","doi":"https://doi.org/10.14778/2536360.2536361","mag":"2043795882"},"language":"en","primary_location":{"id":"doi:10.14778/2536360.2536361","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536360.2536361","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5110197814","display_name":"Flip Korn","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Flip Korn","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110611660","display_name":"Barna Saha","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barna Saha","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020772911","display_name":"Shanshan Ying","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shanshan Ying","raw_affiliation_strings":["Nat'l Univ Singapore"],"affiliations":[{"raw_affiliation_string":"Nat'l Univ Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110197814"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":9.3905,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97709039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":"9","first_page":"601","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8761436939239502},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7352451086044312},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6402007937431335},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5814008116722107},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5255740284919739},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.46551230549812317},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.457735538482666},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.44239652156829834},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4412398636341095},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4346466660499573},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.42578640580177307},{"id":"https://openalex.org/keywords/nesting","display_name":"Nesting (process)","score":0.42525672912597656},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40621888637542725},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40200233459472656},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24776625633239746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8761436939239502},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7352451086044312},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6402007937431335},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5814008116722107},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5255740284919739},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.46551230549812317},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.457735538482666},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.44239652156829834},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4412398636341095},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4346466660499573},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.42578640580177307},{"id":"https://openalex.org/C2776937656","wikidata":"https://www.wikidata.org/wiki/Q2229669","display_name":"Nesting (process)","level":2,"score":0.42525672912597656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40621888637542725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40200233459472656},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24776625633239746},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2536360.2536361","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536360.2536361","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.423.787","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.423.787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/export/sites/att_labs/techdocs/TD_101199.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":35,"referenced_works":["https://openalex.org/W43380317","https://openalex.org/W102254938","https://openalex.org/W1501400124","https://openalex.org/W1512194759","https://openalex.org/W1512553031","https://openalex.org/W1571991326","https://openalex.org/W1647671624","https://openalex.org/W1969005071","https://openalex.org/W1970026646","https://openalex.org/W1976373002","https://openalex.org/W1996878052","https://openalex.org/W2001496424","https://openalex.org/W2003889154","https://openalex.org/W2009056959","https://openalex.org/W2025063099","https://openalex.org/W2031365811","https://openalex.org/W2049216468","https://openalex.org/W2053966137","https://openalex.org/W2058941326","https://openalex.org/W2059078591","https://openalex.org/W2081868109","https://openalex.org/W2112840274","https://openalex.org/W2121843890","https://openalex.org/W2123229843","https://openalex.org/W2127229466","https://openalex.org/W2128381480","https://openalex.org/W2136393336","https://openalex.org/W2147805208","https://openalex.org/W2152593687","https://openalex.org/W2164501930","https://openalex.org/W2167333415","https://openalex.org/W2169131377","https://openalex.org/W6601698896","https://openalex.org/W6630787032","https://openalex.org/W6651584021"],"related_works":["https://openalex.org/W2746923702","https://openalex.org/W2536894089","https://openalex.org/W2357844625","https://openalex.org/W1501142348","https://openalex.org/W2106024890","https://openalex.org/W2128362448","https://openalex.org/W2742873848","https://openalex.org/W2117064692","https://openalex.org/W2401139123","https://openalex.org/W1507976212"],"abstract_inverted_index":{"Semi-structured":[0],"data":[1,8,29,82],"such":[2],"as":[3],"XML":[4,14,39],"are":[5,24,92],"popular":[6],"for":[7],"interchange":[9],"and":[10,22,36,117,124],"storage.":[11],"However,":[12],"many":[13,38],"documents":[15,40],"have":[16,32],"improper":[17],"nesting":[18],"where":[19,95],"open":[20],"-":[21],"close-tags":[23],"unmatched.":[25],"Since":[26],"some":[27],"semi-structured":[28],"(e.g.,":[30],"Latex)":[31],"a":[33,51,64],"flexible":[34],"grammar":[35],"since":[37],"lack":[41],"an":[42],"accompanying":[43],"DTD":[44],"or":[45],"XSD,":[46],"we":[47,62,104,127],"focus":[48],"on":[49,109,135],"computing":[50],"syntactic":[52],"repair":[53],"via":[54],"the":[55,81,96,130],"edit":[56],"distance.":[57],"To":[58],"solve":[59],"this":[60,73],"problem,":[61],"propose":[63],"dynamic":[65,97],"programming":[66],"algorithm":[67,74],"which":[68],"takes":[69],"cubic":[70],"time.":[71],"While":[72],"is":[75],"not":[76],"scalable,":[77],"well-formed":[78],"substrings":[79],"of":[80,112,132],"can":[83],"be":[84,100],"pruned":[85],"to":[86],"enable":[87],"faster":[88],"computation.":[89],"Unfortunately,":[90],"there":[91],"still":[93],"cases":[94],"program":[98],"could":[99],"very":[101],"expensive;":[102],"hence,":[103],"give":[105],"branch-and-bound":[106],"algorithms":[107,134],"based":[108],"various":[110],"combinations":[111],"two":[113],"heuristics,":[114],"called":[115],"MinCost":[116],"MaxBenefit,":[118],"that":[119],"trade":[120],"off":[121],"between":[122],"accuracy":[123],"efficiency.":[125],"Finally,":[126],"experimentally":[128],"demonstrate":[129],"performance":[131],"these":[133],"real":[136],"data.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}