{"id":"https://openalex.org/W2129010478","doi":"https://doi.org/10.1145/1807085.1807122","title":"A learning algorithm for top-down XML transformations","display_name":"A learning algorithm for top-down XML transformations","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2129010478","doi":"https://doi.org/10.1145/1807085.1807122","mag":"2129010478"},"language":"en","primary_location":{"id":"doi:10.1145/1807085.1807122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807085.1807122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00460489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044330058","display_name":"Aur\u00e9lien Lemay","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I174424907","display_name":"Laboratoire d'Informatique Fondamentale de Lille","ror":"https://ror.org/05rhg0h08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I174424907"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aurelien Lemay","raw_affiliation_strings":["University of Lille (LIFL) and INRIA (Mostrare project), Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille (LIFL) and INRIA (Mostrare project), Lille, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I174424907","https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010785818","display_name":"Sebastian Maneth","orcid":"https://orcid.org/0000-0001-8667-5436"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sebastian Maneth","raw_affiliation_strings":["NICTA and UNSW, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NICTA and UNSW, Sydney, Australia","institution_ids":["https://openalex.org/I31746571","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045969205","display_name":"Joachim Niehren","orcid":"https://orcid.org/0000-0002-2611-8950"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I174424907","display_name":"Laboratoire d'Informatique Fondamentale de Lille","ror":"https://ror.org/05rhg0h08","country_code":"FR","type":"facility","lineage":["https://openalex.org/I174424907"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Joachim Niehren","raw_affiliation_strings":["University of Lille (LIFL) and INRIA (Mostrare project), Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille (LIFL) and INRIA (Mostrare project), Lille, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I174424907","https://openalex.org/I2279609970"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.542,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.94217884,"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":"285","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987999796867371,"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/T11567","display_name":"semigroups and automata theory","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7226707339286804},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7003101110458374},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6979373693466187},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5628451108932495},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5493332147598267},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4724567234516144},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4610852599143982},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45455822348594666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4488707184791565},{"id":"https://openalex.org/keywords/regular-language","display_name":"Regular language","score":0.4456598162651062},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4307307004928589},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.2687453627586365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22845321893692017},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18920618295669556},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1549111008644104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226707339286804},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7003101110458374},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6979373693466187},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5628451108932495},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5493332147598267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4724567234516144},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4610852599143982},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45455822348594666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4488707184791565},{"id":"https://openalex.org/C52370388","wikidata":"https://www.wikidata.org/wiki/Q752532","display_name":"Regular language","level":3,"score":0.4456598162651062},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4307307004928589},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.2687453627586365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22845321893692017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18920618295669556},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1549111008644104},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1145/1807085.1807122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807085.1807122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.402.2393","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.402.2393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.grappa.univ-lille3.fr/~niehren/Papers/learn-dtop/long.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.402.2461","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.402.2461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/49/42/10/PDF/0.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.602.3152","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.602.3152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.658.1871","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.658.1871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/inria-00460489/document/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.987.7992","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.987.7992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Aurelien_Lemay/publication/42854407_A_Learning_Algorithm_for_Top-Down_XML_Transformations/links/0c96053c64a84b2ace000000.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.996.4536","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.996.4536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Aurelien_Lemay/publication/42854407_A_Learning_Algorithm_for_Top-Down_XML_Transformations/links/0c96053c64a84b2ace000000.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00460489v2","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00460489","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"29th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, Jun 2010, Indianapolis, United States. pp.285-296","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00460489v2","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00460489","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"29th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, Jun 2010, Indianapolis, United States. pp.285-296","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W147871093","https://openalex.org/W166194785","https://openalex.org/W1484394245","https://openalex.org/W1504220338","https://openalex.org/W1519430564","https://openalex.org/W1816184685","https://openalex.org/W1977578205","https://openalex.org/W1979629711","https://openalex.org/W1988343205","https://openalex.org/W1989445634","https://openalex.org/W1993233874","https://openalex.org/W2013714680","https://openalex.org/W2017603160","https://openalex.org/W2020298184","https://openalex.org/W2035285350","https://openalex.org/W2047303298","https://openalex.org/W2067829889","https://openalex.org/W2086959507","https://openalex.org/W2128517960","https://openalex.org/W2145051847","https://openalex.org/W2150256214","https://openalex.org/W2150365753","https://openalex.org/W2159793945","https://openalex.org/W2162157640","https://openalex.org/W2164592058","https://openalex.org/W2166210475","https://openalex.org/W2183421559","https://openalex.org/W2206957158","https://openalex.org/W3037477934","https://openalex.org/W6687951745","https://openalex.org/W6779969750"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2080152487","https://openalex.org/W2239445980","https://openalex.org/W2995553446","https://openalex.org/W2964091527","https://openalex.org/W1560765090"],"abstract_inverted_index":{"A":[0],"generalization":[1],"from":[2,7,24],"string":[3,60],"to":[4,9,46,52,101,105,130,147],"trees":[5,161],"and":[6,62,90],"languages":[8],"translations":[10],"is":[11,27,80,115,120,127,139,165],"given":[12],"of":[13,41,74,98,159],"the":[14,47,54,109],"classical":[15],"result":[16,143],"that":[17,29],"any":[18,31],"regular":[19],"language":[20],"can":[21,87,144,171],"be":[22,106,145,180],"learned":[23],"examples:":[25],"it":[26,138],"shown":[28,140],"for":[30,59,63,117,135],"deterministic":[32,75],"top-down":[33,76],"tree":[34,66,77],"transformation":[35],"there":[36],"exists":[37],"a":[38,85,112,132,155],"sample":[39],"set":[40],"polynomial":[42],"size":[43],"(with":[44],"respect":[45],"minimal":[48],"transducer)":[49],"which":[50,119,178],"allows":[51],"infer":[53],"translation.":[55],"Until":[56],"now,":[57],"only":[58],"transducers":[61,78],"simple":[64],"relabeling":[65],"transducers,":[67],"similar":[68],"results":[69],"had":[70],"been":[71],"known.":[72],"Learning":[73],"(dtops)":[79],"far":[81],"more":[82],"involved":[83],"because":[84],"dtop":[86],"copy,":[88],"delete,":[89],"permute":[91],"its":[92,123],"input":[93,100],"subtrees.":[94],"Thus,":[95],"complex":[96],"dependencies":[97],"labeled":[99],"output":[102],"paths":[103],"need":[104],"maintained":[107],"by":[108,162],"algorithm.":[110],"First,":[111],"Myhill-Nerode":[113],"theorem":[114,126],"presented":[116],"dtops,":[118],"interesting":[121,175],"on":[122,182],"own.":[124],"This":[125],"then":[128],"used":[129],"construct":[131],"learning":[133],"algorithm":[134],"dtops.":[136],"Finally,":[137],"how":[141],"our":[142],"applied":[146],"xml":[148,176],"transformations":[149,177],"(e.g.":[150],"xslt":[151],"programs).":[152],"For":[153],"this,":[154],"new":[156],"dtd-based":[157],"encoding":[158],"unranked":[160],"ranked":[163],"ones":[164],"presented.":[166],"Over":[167],"such":[168],"encodings,":[169],"dtops":[170],"realize":[172],"many":[173],"practically":[174],"cannot":[179],"realized":[181],"firstchild/next-sibling":[183],"encodings.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}