{"id":"https://openalex.org/W2047342127","doi":"https://doi.org/10.1145/1135777.1135891","title":"Compressing and searching XML data via two zips","display_name":"Compressing and searching XML data via two zips","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2047342127","doi":"https://doi.org/10.1145/1135777.1135891","mag":"2047342127"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5046786328","display_name":"Paolo Ferragina","orcid":"https://orcid.org/0000-0003-1353-360X"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"P. Ferragina","raw_affiliation_strings":["Univ. Pisa"],"affiliations":[{"raw_affiliation_string":"Univ. Pisa","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006557955","display_name":"Fabrizio Luccio","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"F. Luccio","raw_affiliation_strings":["Univ. Pisa"],"affiliations":[{"raw_affiliation_string":"Univ. Pisa","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049381844","display_name":"Giovanni Manzini","orcid":"https://orcid.org/0000-0002-5047-0196"},"institutions":[{"id":"https://openalex.org/I123338534","display_name":"Universit\u00e0 degli Studi del Piemonte Orientale \u201cAmedeo Avogadro\u201d","ror":"https://ror.org/04387x656","country_code":"IT","type":"education","lineage":["https://openalex.org/I123338534"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"G. Manzini","raw_affiliation_strings":["Univ. Piemonte Orientale"],"affiliations":[{"raw_affiliation_string":"Univ. Piemonte Orientale","institution_ids":["https://openalex.org/I123338534"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045502987","display_name":"S. Muthukrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Rutgers Univ","Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers Univ","institution_ids":["https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046786328"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":19.5387,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99365721,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"751","last_page":"760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.8799926042556763},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.866520345211029},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.8549737930297852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8238488435745239},{"id":"https://openalex.org/keywords/xml-encryption","display_name":"XML Encryption","score":0.7986350059509277},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.7558798789978027},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.7526460886001587},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.6923099160194397},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.6864447593688965},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.615253746509552},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.5972840189933777},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5864171385765076},{"id":"https://openalex.org/keywords/xml-framework","display_name":"XML framework","score":0.5831112861633301},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5304811596870422},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3559034466743469},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20476439595222473}],"concepts":[{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.8799926042556763},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.866520345211029},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.8549737930297852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238488435745239},{"id":"https://openalex.org/C173242113","wikidata":"https://www.wikidata.org/wiki/Q607488","display_name":"XML Encryption","level":4,"score":0.7986350059509277},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.7558798789978027},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.7526460886001587},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.6923099160194397},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.6864447593688965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.615253746509552},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.5972840189933777},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5864171385765076},{"id":"https://openalex.org/C21761406","wikidata":"https://www.wikidata.org/wiki/Q8042330","display_name":"XML framework","level":3,"score":0.5831112861633301},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5304811596870422},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3559034466743469},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20476439595222473}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1135777.1135891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.5212","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.5212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.di.unipmn.it/Tecnical-R/Technical-3/TR-INF-2005/tr-www06-4.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.47","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mfn.unipmn.it/~manzini/papers/www06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.5791","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.5791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2006.org/programme/files/pdf/6009.pdf","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/189125","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/189125","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W207177372","https://openalex.org/W1515993376","https://openalex.org/W1517592599","https://openalex.org/W1523411787","https://openalex.org/W1566656449","https://openalex.org/W1887246875","https://openalex.org/W1896196855","https://openalex.org/W2013849299","https://openalex.org/W2035902703","https://openalex.org/W2037089206","https://openalex.org/W2044014345","https://openalex.org/W2045371954","https://openalex.org/W2090970745","https://openalex.org/W2096339352","https://openalex.org/W2118486794","https://openalex.org/W2122530852","https://openalex.org/W2128242733","https://openalex.org/W2132555066","https://openalex.org/W2134356404","https://openalex.org/W2135432866","https://openalex.org/W2139911998","https://openalex.org/W2140907203","https://openalex.org/W2148113067","https://openalex.org/W2152354466","https://openalex.org/W2159647614","https://openalex.org/W2161967451","https://openalex.org/W2202508117","https://openalex.org/W4235095233","https://openalex.org/W6608363685","https://openalex.org/W6631497757","https://openalex.org/W6639764667","https://openalex.org/W6661990957"],"related_works":["https://openalex.org/W3194587731","https://openalex.org/W2024164996","https://openalex.org/W2276215951","https://openalex.org/W1591876566","https://openalex.org/W1530834279","https://openalex.org/W56340752","https://openalex.org/W2347497444","https://openalex.org/W1912491515","https://openalex.org/W2251451180","https://openalex.org/W2359140806"],"abstract_inverted_index":{"XML":[0,25,30,70,99,136,147,194,202],"is":[1,16,35,101,182],"fast":[2],"becoming":[3],"the":[4,13,43,61,98,122,135,164],"standard":[5,201],"format":[6],"to":[7,85,152,160],"store,":[8],"exchange":[9],"and":[10,15,42,52,67,87,108,111,129,149,171,178],"publish":[11],"over":[12,189],"web,":[14],"getting":[17],"embedded":[18],"in":[19,23,96,103],"applications.":[20],"Two":[21],"challenges":[22],"handling":[24],"are":[26],"its":[27,39,46,172],"size":[28],"(the":[29],"representation":[31],"of":[32,45,64,69,121,184,191,193,198],"a":[33,89,104,118],"document":[34,100],"significantly":[36],"larger":[37],"than":[38,163],"native":[40],"state)":[41],"complexity":[44],"search":[47,49,180],"(XML":[48],"involves":[50],"path":[51,177],"content":[53,179],"searches":[54],"on":[55,127,175,200],"labeled":[56],"tree":[57,83],"structures).":[58],"We":[59],"address":[60],"basic":[62],"problems":[63],"compression,":[65],"navigation":[66,110],"searching":[68,112,150],"documents.":[71],"In":[72],"particular,":[73],"we":[74,141],"adopt":[75],"recently":[76],"proposed":[77],"theoretical":[78],"algorithms":[79],"[11]":[80],"for":[81,92],"succinct":[82],"representations":[84],"design":[86],"implement":[88],"compressed":[90,106,146],"index":[91],"XML,":[93],"called":[94],"XBZIPiNDEX,":[95],"which":[97],"maintained":[102],"highly":[105],"format,":[107],"both":[109],"can":[113],"be":[114],"done":[115],"uncompressing":[116],"only":[117],"tiny":[119],"fraction":[120],"data.":[123,137],"This":[124],"solution":[125],"relies":[126],"compressing":[128],"indexing":[130,148],"two":[131],"arrays":[132],"derived":[133],"from":[134],"With":[138],"detailed":[139],"experiments":[140],"compare":[142],"this":[143],"with":[144],"other":[145,169],"engines":[151],"show":[153],"that":[154],"XBZIPiNDEX":[155],"has":[156],"compression":[157],"ratio":[158],"up":[159],"35%":[161],"better":[162],"ones":[165],"achievable":[166],"by":[167],"those":[168],"tools,":[170],"time":[173],"performance":[174],"some":[176],"operations":[181],"order":[183],"magnitudes":[185],"faster:":[186],"few":[187],"milliseconds":[188],"hundreds":[190],"MBs":[192],"files":[195],"versus":[196],"tens":[197],"seconds,":[199],"data":[203],"sources.":[204]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
