{"id":"https://openalex.org/W2047303298","doi":"https://doi.org/10.1145/1367497.1367609","title":"Learning deterministic regular expressions for the inference of schemas from XML data","display_name":"Learning deterministic regular expressions for the inference of schemas from XML data","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2047303298","doi":"https://doi.org/10.1145/1367497.1367609","mag":"2047303298"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1942/8500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010031379","display_name":"Geert Jan Bex","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Geert Jan Bex","raw_affiliation_strings":["Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089107114","display_name":"Wouter Gelade","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wouter Gelade","raw_affiliation_strings":["Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022264843","display_name":"Frank Neven","orcid":"https://orcid.org/0000-0002-7143-1903"},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Frank Neven","raw_affiliation_strings":["Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022558461","display_name":"Stijn Vansummeren","orcid":"https://orcid.org/0000-0001-7793-9049"},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Vansummeren","raw_affiliation_strings":["Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University/Transnational University of Limburg, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.295,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97462222,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"825","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9980999827384949,"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":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947989463806152},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6318576335906982},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5750812292098999},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5382101535797119},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4823974370956421},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46396908164024353},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4481580853462219},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.43816179037094116},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4182429611682892},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3927875757217407},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3271271288394928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31544965505599976},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.18437379598617554},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15913227200508118},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15322420001029968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947989463806152},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6318576335906982},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5750812292098999},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5382101535797119},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4823974370956421},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46396908164024353},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4481580853462219},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.43816179037094116},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4182429611682892},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3927875757217407},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3271271288394928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31544965505599976},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.18437379598617554},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15913227200508118},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15322420001029968},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1367497.1367609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:dipot.ulb.ac.be:2013/172382","is_oa":false,"landing_page_url":"http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/172382","pdf_url":null,"source":{"id":"https://openalex.org/S4306401063","display_name":"D\u00e9p\u00f4t institutionnel de l'Universit\u00e9 libre de Bruxelles (Universit\u00e9 Libre de Bruxelles)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I132053463","host_organization_name":"Universit\u00e9 Libre de Bruxelles","host_organization_lineage":["https://openalex.org/I132053463"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Proceedings of the 17th International Conference on World Wide Web, WWW '08. ACM Press","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/8500","is_oa":true,"landing_page_url":"http://hdl.handle.net/1942/8500","pdf_url":null,"source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:documentserver.uhasselt.be:1942/8500","is_oa":true,"landing_page_url":"http://hdl.handle.net/1942/8500","pdf_url":null,"source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1482220696","https://openalex.org/W1489016619","https://openalex.org/W1517529647","https://openalex.org/W1542184482","https://openalex.org/W1556528519","https://openalex.org/W1560635010","https://openalex.org/W1578784159","https://openalex.org/W1595778895","https://openalex.org/W1607995248","https://openalex.org/W1662087476","https://openalex.org/W1908950999","https://openalex.org/W1969005071","https://openalex.org/W2002089154","https://openalex.org/W2006061474","https://openalex.org/W2008896880","https://openalex.org/W2024295392","https://openalex.org/W2030033535","https://openalex.org/W2031469331","https://openalex.org/W2047303298","https://openalex.org/W2057185776","https://openalex.org/W2057841333","https://openalex.org/W2061079066","https://openalex.org/W2066064214","https://openalex.org/W2080947572","https://openalex.org/W2082135413","https://openalex.org/W2099540492","https://openalex.org/W2105748890","https://openalex.org/W2107741633","https://openalex.org/W2108350934","https://openalex.org/W2108543348","https://openalex.org/W2109486375","https://openalex.org/W2117789898","https://openalex.org/W2123229843","https://openalex.org/W2125822162","https://openalex.org/W2125838338","https://openalex.org/W2134356404","https://openalex.org/W2136280642","https://openalex.org/W2137580272","https://openalex.org/W2141724398","https://openalex.org/W2145948275","https://openalex.org/W2148832586","https://openalex.org/W2154475850","https://openalex.org/W2164765168","https://openalex.org/W2166194842","https://openalex.org/W2169028468","https://openalex.org/W2169131377","https://openalex.org/W2500135585","https://openalex.org/W2963696918","https://openalex.org/W2998389348","https://openalex.org/W3104723580","https://openalex.org/W4246406856","https://openalex.org/W4254661725","https://openalex.org/W4285719527","https://openalex.org/W6662372857","https://openalex.org/W6668684869","https://openalex.org/W6678385900","https://openalex.org/W6684695314","https://openalex.org/W6724150780"],"related_works":["https://openalex.org/W1600174612","https://openalex.org/W56340752","https://openalex.org/W2013920494","https://openalex.org/W2378161351","https://openalex.org/W2591795766","https://openalex.org/W4283736786","https://openalex.org/W2121785123","https://openalex.org/W2376675693","https://openalex.org/W1533091132","https://openalex.org/W1970085714"],"abstract_inverted_index":{"Inferring":[0],"an":[1],"appropriate":[2],"DTD":[3],"or":[4],"XML":[5,14],"Schema":[6],"Definition":[7],"(XSD)":[8],"for":[9,98,112,126],"a":[10,70,120,142],"given":[11],"collection":[12],"of":[13,25,35,40,73,85,129,149,174],"documents":[15],"essentially":[16],"reduces":[17],"to":[18,81,104,167],"learning":[19,36],"deterministic":[20,41],"regular":[21,42,53,86,109],"expressions":[22,43,54,87,106,110,175],"from":[23,44],"sets":[24],"positive":[26,45],"example":[27],"words.":[28],"Unfortunately,":[29],"there":[30],"is":[31,152,165],"no":[32],"algorithm":[33,122],"capable":[34],"the":[37,83,133,138,150,163,171],"complete":[38],"class":[39],"examples":[46],"only,":[47],"as":[48,107],"we":[49,118],"will":[50],"show.":[51],"The":[52,147],"occurring":[55],"in":[56,77,88,177],"practical":[57],"DTDs":[58],"and":[59,131,159],"XSDs,":[60],"however,":[61],"are":[62],"such":[63,105],"that":[64,123,135],"every":[65],"alphabet":[66,91],"symbol":[67,92],"occurs":[68,93],"only":[69],"small":[71,100],"number":[72],"times.":[74],"As":[75],"such,":[76],"practice":[78],"it":[79],"suffices":[80],"learn":[82],"subclass":[84],"which":[89],"each":[90],"at":[94],"most":[95],"k":[96],"times,":[97],"some":[99],"k.":[101],"We":[102],"refer":[103],"k-occurrence":[108],"(k-OREs":[111],"short).":[113],"Motivated":[114],"by":[115],"this":[116],"observation,":[117],"provide":[119],"probabilistic":[121],"learns":[124],"k-OREs":[125],"increasing":[127],"values":[128],"k,":[130],"selects":[132],"one":[134],"best":[136],"describes":[137],"sample":[139],"based":[140],"on":[141,156],"Minimum":[143],"Description":[144],"Length":[145],"argument.":[146],"effectiveness":[148],"method":[151,164],"empirically":[153],"validated":[154],"both":[155],"real":[157],"world":[158],"synthetic":[160],"data.":[161],"Furthermore,":[162],"shown":[166],"be":[168],"conservative":[169],"over":[170],"simpler":[172],"classes":[173],"considered":[176],"previous":[178],"work.":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}