{"id":"https://openalex.org/W2033629528","doi":"https://doi.org/10.1145/1670243.1670247","title":"The pq -gram distance between ordered labeled trees","display_name":"The pq -gram distance between ordered labeled trees","publication_year":2008,"publication_date":"2008-02-15","ids":{"openalex":"https://openalex.org/W2033629528","doi":"https://doi.org/10.1145/1670243.1670247","mag":"2033629528"},"language":"en","primary_location":{"id":"doi:10.1145/1670243.1670247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1670243.1670247","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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 Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.zora.uzh.ch/id/eprint/44572/1/a4-augsten.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089328860","display_name":"Nikolaus Augsten","orcid":"https://orcid.org/0000-0002-3036-6201"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nikolaus Augsten","raw_affiliation_strings":["Free University of Bozen-Bolzano, Bozen-Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017018305","display_name":"Michael H. B\u00f6hlen","orcid":"https://orcid.org/0000-0003-3694-9026"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michael B\u00f6hlen","raw_affiliation_strings":["Free University of Bozen-Bolzano, Bozen-Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043864804","display_name":"Johann Gamper","orcid":"https://orcid.org/0000-0002-7128-507X"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Johann Gamper","raw_affiliation_strings":["Free University of Bozen-Bolzano, Bozen-Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bozen-Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I171543936"],"apc_list":null,"apc_paid":null,"fwci":4.7047,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.94173328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.8326115608215332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897473573684692},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6897276043891907},{"id":"https://openalex.org/keywords/triangle-inequality","display_name":"Triangle inequality","score":0.652290940284729},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.6466805338859558},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6274486184120178},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6023085117340088},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5215280055999756},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5112259387969971},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.43483203649520874},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4293994605541229},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3992879390716553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3734620213508606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007381856441498},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17192569375038147},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.152032732963562},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1447020173072815}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8326115608215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897473573684692},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6897276043891907},{"id":"https://openalex.org/C182964748","wikidata":"https://www.wikidata.org/wiki/Q208216","display_name":"Triangle inequality","level":2,"score":0.652290940284729},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.6466805338859558},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6274486184120178},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6023085117340088},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5215280055999756},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5112259387969971},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.43483203649520874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4293994605541229},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3992879390716553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3734620213508606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007381856441498},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17192569375038147},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.152032732963562},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1447020173072815},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1670243.1670247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1670243.1670247","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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 Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:www.zora.uzh.ch:44572","is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/id/eprint/44572/1/a4-augsten.pdf","pdf_url":"https://www.zora.uzh.ch/id/eprint/44572/1/a4-augsten.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"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":"Augsten, N; B\u00f6hlen, M; Gamper, J (2010). The pq-gram distance between ordered labeled trees. ACM Transactions on Database Systems (TODS), 35(1):4:1-4:36.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:unibz.it:11234989680001241","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/1670243.1670247","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"Open Research (University of Surrey)","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.5167/uzh-44572","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-44572","pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:www.zora.uzh.ch:44572","is_oa":true,"landing_page_url":"https://www.zora.uzh.ch/id/eprint/44572/1/a4-augsten.pdf","pdf_url":"https://www.zora.uzh.ch/id/eprint/44572/1/a4-augsten.pdf","source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"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":"Augsten, N; B\u00f6hlen, M; Gamper, J (2010). The pq-gram distance between ordered labeled trees. ACM Transactions on Database Systems (TODS), 35(1):4:1-4:36.","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2033629528.pdf","grobid_xml":"https://content.openalex.org/works/W2033629528.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W160875351","https://openalex.org/W180687025","https://openalex.org/W182666420","https://openalex.org/W299839057","https://openalex.org/W1481200545","https://openalex.org/W1486753193","https://openalex.org/W1558455905","https://openalex.org/W1605903931","https://openalex.org/W1628571627","https://openalex.org/W1845040079","https://openalex.org/W1866266163","https://openalex.org/W1875883055","https://openalex.org/W1975009259","https://openalex.org/W1976373002","https://openalex.org/W1978510388","https://openalex.org/W1978569932","https://openalex.org/W1994694191","https://openalex.org/W1996186909","https://openalex.org/W2001496424","https://openalex.org/W2024797550","https://openalex.org/W2043481183","https://openalex.org/W2046953300","https://openalex.org/W2048001624","https://openalex.org/W2049461910","https://openalex.org/W2061884758","https://openalex.org/W2065290081","https://openalex.org/W2085533860","https://openalex.org/W2107412086","https://openalex.org/W2109464129","https://openalex.org/W2111087864","https://openalex.org/W2111110587","https://openalex.org/W2113836856","https://openalex.org/W2114642041","https://openalex.org/W2123645388","https://openalex.org/W2128381480","https://openalex.org/W2133491514","https://openalex.org/W2136393336","https://openalex.org/W2147828873","https://openalex.org/W2147909264","https://openalex.org/W2156664231","https://openalex.org/W2161675403","https://openalex.org/W2161936973","https://openalex.org/W2164501930","https://openalex.org/W2491780404","https://openalex.org/W2561675875","https://openalex.org/W2737168042","https://openalex.org/W3021133423"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2088254117","https://openalex.org/W159237226","https://openalex.org/W4254593385","https://openalex.org/W2156279557","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W2102177745","https://openalex.org/W2352409255"],"abstract_inverted_index":{"When":[0],"integrating":[1],"data":[2,9,63,128],"from":[3,64],"autonomous":[4,65],"sources,":[5],"exact":[6],"matches":[7],"of":[8,23,83,101,112,136,143],"items":[10],"that":[11,92],"represent":[12],"the":[13,43,49,52,69,84,93,102,113,119,134,141],"same":[14],"real-world":[15,127],"object":[16],"often":[17],"fail":[18],"due":[19],"to":[20,38,59],"a":[21,98,110],"lack":[22],"common":[24],"keys.":[25],"Yet":[26],"in":[27,51],"many":[28],"cases":[29],"structural":[30],"information":[31],"is":[32,97],"available":[33],"and":[34,67,80,108,126,131,139],"can":[35],"be":[36,46],"used":[37],"match":[39,61],"such":[40],"data.":[41],"Typically":[42],"matching":[44],"must":[45],"approximate":[47],"since":[48],"representations":[50],"sources":[53,66],"differ.":[54],"We":[55,90],"propose":[56],"pq":[57,70,94,114,144],"-grams":[58],"approximately":[60],"hierarchical":[62],"define":[68],"-gram":[71,95,115],"distance":[72,96,107,116],"between":[73],"ordered":[74],"labeled":[75],"trees":[76],"as":[77],"an":[78],"effective":[79],"efficient":[81],"approximation":[82],"fanout":[85,103],"weighted":[86,104],"tree":[87,105],"edit":[88,106],"distance.":[89],"prove":[91],"lower":[99],"bound":[100],"give":[109],"normalization":[111],"for":[117],"which":[118],"triangle":[120],"inequality":[121],"holds.":[122],"Experiments":[123],"on":[124],"synthetic":[125],"(residential":[129],"addresses":[130],"XML)":[132],"confirm":[133],"scalability":[135],"our":[137],"approach":[138],"show":[140],"effectiveness":[142],"-grams.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":7}],"updated_date":"2026-09-01T08:31:24.195828","created_date":"2025-10-10T00:00:00"}