{"id":"https://openalex.org/W2569219525","doi":"https://doi.org/10.1145/1841909.1841911","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":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2569219525","doi":"https://doi.org/10.1145/1841909.1841911","mag":"2569219525"},"language":"en","primary_location":{"id":"doi:10.1145/1841909.1841911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1841909.1841911","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"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":"ACM Transactions on the Web","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/A5010031379","display_name":"Geert Jan Bex","orcid":null},"institutions":[{"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 and Transnational University of Limburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University and Transnational University of Limburg","institution_ids":["https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089107114","display_name":"Wouter Gelade","orcid":null},"institutions":[{"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 and Transnational University of Limburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University and Transnational University of Limburg","institution_ids":["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/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 and Transnational University of Limburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University and Transnational University of Limburg","institution_ids":["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/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Vansummeren","raw_affiliation_strings":["Universit\u00e9 Libre de Bruxelles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Libre de Bruxelles","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.3147,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.98644034,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.7307488918304443},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6055846810340881},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5394623279571533},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5367587208747864},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5030850768089294},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46282464265823364},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4565228819847107},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4153686761856079},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41423895955085754},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.4118977189064026},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4012643098831177},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33381175994873047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26748159527778625},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.17013388872146606},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15429547429084778},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1451413631439209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307488918304443},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6055846810340881},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5394623279571533},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5367587208747864},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5030850768089294},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46282464265823364},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4565228819847107},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4153686761856079},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41423895955085754},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.4118977189064026},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4012643098831177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33381175994873047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26748159527778625},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.17013388872146606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15429547429084778},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1451413631439209},{"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:10.1145/1841909.1841911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1841909.1841911","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"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":"ACM Transactions on the Web","raw_type":"journal-article"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/11295","is_oa":false,"landing_page_url":"http://hdl.handle.net/1942/11295","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G582362311","display_name":null,"funder_award_id":"FP7-ICT-233599","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W421997344","https://openalex.org/W1482220696","https://openalex.org/W1489016619","https://openalex.org/W1527356121","https://openalex.org/W1536741282","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/W1985578047","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/W2063985934","https://openalex.org/W2066064214","https://openalex.org/W2082135413","https://openalex.org/W2099540492","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/W2913208717","https://openalex.org/W2915063781","https://openalex.org/W2963696918","https://openalex.org/W2998389348","https://openalex.org/W3104723580","https://openalex.org/W4205241946","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1600174612","https://openalex.org/W56340752","https://openalex.org/W2013920494","https://openalex.org/W1880452510","https://openalex.org/W2378161351","https://openalex.org/W2121785123","https://openalex.org/W1970085714","https://openalex.org/W2591795766","https://openalex.org/W4283736786","https://openalex.org/W2376675693"],"abstract_inverted_index":{"Inferring":[0],"an":[1],"appropriate":[2],"DTD":[3],"or":[4],"XML":[5,14],"Schema":[6],"Definition":[7],"(XSD)":[8],"for":[9,99,117,132],"a":[10,70,125,149],"given":[11],"collection":[12],"of":[13,25,35,40,73,85,135,156,181],"documents":[15],"essentially":[16],"reduces":[17],"to":[18,81,106,174],"learning":[19,36],"deterministic":[20,41,86,140],"regular":[21,42,53,87,112],"expressions":[22,43,54,88,108,113,182],"from":[23,44],"sets":[24],"positive":[26,45],"example":[27],"words.":[28],"Unfortunately,":[29],"there":[30],"is":[31,159,172],"no":[32],"algorithm":[33,127],"capable":[34],"the":[37,83,139,145,157,170,178],"complete":[38],"class":[39],"examples":[46],"only,":[47],"as":[48,109],"we":[49,123],"will":[50],"show.":[51],"The":[52,154],"occurring":[55],"in":[56,77,89,184],"practical":[57],"DTDs":[58],"and":[59,137,166],"XSDs,":[60],"however,":[61],"are":[62],"such":[63,107],"that":[64,128,142],"every":[65],"alphabet":[66,92],"symbol":[67,93],"occurs":[68,94],"only":[69],"small":[71,101],"number":[72],"times.":[74],"As":[75],"such,":[76],"practice":[78],"it":[79],"suffices":[80],"learn":[82],"subclass":[84],"which":[90],"each":[91],"at":[95],"most":[96],"k":[97,102,110,115,130],"times,":[98],"some":[100],".":[103],"We":[104],"refer":[105],"-occurrence":[111],"(":[114],"-OREs":[116,131],"short).":[118],"Motivated":[119],"by":[120],"this":[121],"observation,":[122],"provide":[124],"probabilistic":[126],"learns":[129],"increasing":[133],"values":[134],"k,":[136],"selects":[138],"one":[141],"best":[143],"describes":[144],"sample":[146],"based":[147],"on":[148,163],"Minimum":[150],"Description":[151],"Length":[152],"argument.":[153],"effectiveness":[155],"method":[158,171],"empirically":[160],"validated":[161],"both":[162],"real":[164],"world":[165],"synthetic":[167],"data.":[168],"Furthermore,":[169],"shown":[173],"be":[175],"conservative":[176],"over":[177],"simpler":[179],"classes":[180],"considered":[183],"previous":[185],"work.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}