{"id":"https://openalex.org/W2160923181","doi":"https://doi.org/10.1109/icde.2004.1320003","title":"Selectivity estimation for XML twigs","display_name":"Selectivity estimation for XML twigs","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2160923181","doi":"https://doi.org/10.1109/icde.2004.1320003","mag":"2160923181"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1320003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-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/A5010950113","display_name":"Neoklis Polyzotis","orcid":"https://orcid.org/0000-0002-2694-8591"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"N. Polyzotis","raw_affiliation_strings":["University of California, Santa Cruz, USA","University of Wisconsin, Madison, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, USA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of Wisconsin, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023079617","display_name":"Minos Garofalakis","orcid":"https://orcid.org/0000-0003-0285-3907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Garofalakis","raw_affiliation_strings":["Bell Laboratories, Lucent Technologies, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Bell Laboratories, Lucent Technologies, Inc., USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084870386","display_name":"Yannis Ioannidis","orcid":"https://orcid.org/0000-0002-1705-8247"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Y. Ioannidis","raw_affiliation_strings":["University of Athens (NKUA), Greece"],"affiliations":[{"raw_affiliation_string":"University of Athens (NKUA), Greece","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010950113"],"corresponding_institution_ids":["https://openalex.org/I135310074","https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":5.9776,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.9651553,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998999834060669,"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/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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":0.8633782863616943},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7582848072052002},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.734190821647644},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.624789297580719},{"id":"https://openalex.org/keywords/twig","display_name":"Twig","score":0.5598341226577759},{"id":"https://openalex.org/keywords/path-expression","display_name":"Path expression","score":0.5473277568817139},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.542993426322937},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5180140137672424},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5150749087333679},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.514768123626709},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5000035762786865},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48711109161376953},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.43540632724761963},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.43077442049980164},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4107622802257538},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3399408459663391},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.27064475417137146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13765138387680054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09639111161231995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633782863616943},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7582848072052002},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.734190821647644},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.624789297580719},{"id":"https://openalex.org/C2777601135","wikidata":"https://www.wikidata.org/wiki/Q11162356","display_name":"Twig","level":2,"score":0.5598341226577759},{"id":"https://openalex.org/C61114434","wikidata":"https://www.wikidata.org/wiki/Q7144649","display_name":"Path expression","level":3,"score":0.5473277568817139},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.542993426322937},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5180140137672424},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5150749087333679},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.514768123626709},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5000035762786865},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48711109161376953},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.43540632724761963},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.43077442049980164},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4107622802257538},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3399408459663391},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.27064475417137146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13765138387680054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09639111161231995},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C144027150","wikidata":"https://www.wikidata.org/wiki/Q48803","display_name":"Horticulture","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},{"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:10.1109/icde.2004.1320003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.4510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.4510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucsc.edu/~alkis/papers/icde04-twigxsketches.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W13024833","https://openalex.org/W44987379","https://openalex.org/W119813091","https://openalex.org/W172857819","https://openalex.org/W1537369822","https://openalex.org/W1581547316","https://openalex.org/W1975887898","https://openalex.org/W1998244781","https://openalex.org/W2000154402","https://openalex.org/W2099132625","https://openalex.org/W2112056262","https://openalex.org/W2132560950","https://openalex.org/W2134585533","https://openalex.org/W2148832586","https://openalex.org/W2156210689","https://openalex.org/W2160923181","https://openalex.org/W2168865746","https://openalex.org/W2171903035","https://openalex.org/W4234667859","https://openalex.org/W4246006899","https://openalex.org/W6600545078","https://openalex.org/W6601863199","https://openalex.org/W6632092688","https://openalex.org/W6634880912","https://openalex.org/W6679745300","https://openalex.org/W6679965934","https://openalex.org/W6682558128"],"related_works":["https://openalex.org/W1983953208","https://openalex.org/W2016456293","https://openalex.org/W1534104849","https://openalex.org/W2136834295","https://openalex.org/W2048497404","https://openalex.org/W2068852373","https://openalex.org/W2161128265","https://openalex.org/W2397337643","https://openalex.org/W2128582123","https://openalex.org/W2394321346"],"abstract_inverted_index":{"Twig":[0],"queries":[1,48,72,116,197],"represent":[2,153],"the":[3,21,33,43,51,68,86,95,101,112,129,148,169,172,228],"building":[4],"blocks":[5],"of":[6,20,28,38,46,53,70,100,114,136,161,171,230],"declarative":[7,71],"query":[8,15],"languages":[9],"over":[10,73,121,198,237],"XML":[11],"data.":[12,123],"A":[13],"twig":[14,47,115,196],"describes":[16],"a":[17,26,57,62,158,178,214],"complex":[18,118,141],"traversal":[19],"document":[22,87],"graph":[23,88],"and":[24,89,97,107,202,223,233],"generates":[25],"set":[27],"element":[29,174],"tuples":[30,54],"based":[31,127],"on":[32,128,168],"intertwined":[34],"evaluation":[35],"(i.e.,":[36],"join)":[37],"multiple":[39],"path":[40,162],"expressions.":[41],"Estimating":[42],"result":[44],"cardinality":[45],"or,":[49],"equivalently,":[50],"number":[52],"in":[55,67,157,189],"such":[56,91],"structural":[58,145],"(path-based)":[59],"join,":[60],"is":[61,76,126,151],"fundamental":[63],"problem":[64],"that":[65,84,164,181],"arises":[66],"optimization":[69],"XML.":[74],"It":[75],"crucial,":[77],"therefore,":[78],"to":[79,152,191],"develop":[80,177],"concise":[81,199],"synopsis":[82],"structures":[83],"summarize":[85],"enable":[90],"selectivity":[92,113,193],"estimates":[93,194],"within":[94],"time":[96],"space":[98,160,216],"constraints":[99],"optimizer.":[102],"We":[103,176],"propose":[104],"novel":[105],"summarization":[106],"estimation":[108],"techniques":[109],"for":[110,139,195,208,213],"estimating":[111],"with":[117,133,185,220],"XPath":[119],"expressions":[120],"tree-structured":[122],"Our":[124],"approach":[125,232],"XSKETCH":[130,200],"model,":[131],"augmented":[132],"new":[134],"types":[135],"distribution":[137,183],"information":[138,167,184],"capturing":[140],"correlation":[142],"patterns":[143],"across":[144],"joins.":[146],"Briefly,":[147],"key":[149],"idea":[150],"joins":[154],"as":[155],"points":[156],"multidimensional":[159],"counts":[163],"capture":[165],"aggregate":[166],"contents":[170],"resulting":[173],"tuples.":[175],"systematic":[179],"framework":[180],"combines":[182],"appropriate":[186],"statistical":[187],"assumptions":[188],"order":[190],"provide":[192],"synopses":[201],"we":[203],"describe":[204],"an":[205,210],"efficient":[206],"algorithm":[207],"constructing":[209],"accurate":[211],"summary":[212],"given":[215],"budget.":[217],"Implementation":[218],"results":[219],"both":[221],"synthetic":[222],"real-life":[224],"data":[225],"sets":[226],"verify":[227],"effectiveness":[229],"our":[231],"demonstrate":[234],"its":[235],"benefits":[236],"earlier":[238],"techniques.":[239]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}