{"id":"https://openalex.org/W2060990214","doi":"https://doi.org/10.1145/1851476.1851591","title":"Massive Semantic Web data compression with MapReduce","display_name":"Massive Semantic Web data compression with MapReduce","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W2060990214","doi":"https://doi.org/10.1145/1851476.1851591","mag":"2060990214"},"language":"en","primary_location":{"id":"doi:10.1145/1851476.1851591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","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/A5090620447","display_name":"Jacopo Urbani","orcid":"https://orcid.org/0000-0002-0717-3559"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jacopo Urbani","raw_affiliation_strings":["Vrije Universiteit, Amsterdam","Vrije Universiteit Amsterdam ,"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit, Amsterdam","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Vrije Universiteit Amsterdam ,","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049957239","display_name":"Jason Maassen","orcid":"https://orcid.org/0000-0002-8172-4865"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jason Maassen","raw_affiliation_strings":["Vrije Universiteit, Amsterdam","Vrije Universiteit Amsterdam ,"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit, Amsterdam","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Vrije Universiteit Amsterdam ,","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055231636","display_name":"Henri E. Bal","orcid":"https://orcid.org/0000-0001-9827-4461"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henri Bal","raw_affiliation_strings":["Vrije Universiteit, Amsterdam","Vrije Universiteit Amsterdam ,"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit, Amsterdam","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Vrije Universiteit Amsterdam ,","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090620447"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":7.8235,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97553648,"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":"795","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9957000017166138,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9957000017166138,"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/T11478","display_name":"Caching and Content Delivery","score":0.9902999997138977,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8908326029777527},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6818620562553406},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5906053185462952},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5891500115394592},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5844191908836365},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.5767714977264404},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5217617154121399},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45832717418670654},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.4225090742111206},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3537403345108032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25322872400283813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8908326029777527},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6818620562553406},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5906053185462952},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5891500115394592},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5844191908836365},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5767714977264404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5217617154121399},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45832717418670654},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.4225090742111206},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3537403345108032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25322872400283813},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1851476.1851591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/2c7dd7a0-0756-4531-8126-70e1de9960fa","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/2c7dd7a0-0756-4531-8126-70e1de9960fa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Urbani, J, Maassen, J & Bal, H E 2010, Massive Semantic Web data compression with MapReduce. in Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010. ACM.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.3675","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.3675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.few.vu.nl/%7Ejui200/papers/HPDC10-mapreduce.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.5155","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.5155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.vu.nl/%7Ejason/papers/HPDC10-mapreduce.pdf","raw_type":"text"},{"id":"pmh:oai:research.vu.nl:publications/2c7dd7a0-0756-4531-8126-70e1de9960fa","is_oa":false,"landing_page_url":"https://hdl.handle.net/1871.1/2c7dd7a0-0756-4531-8126-70e1de9960fa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Urbani, J, Maassen, J & Bal, H E 2010, Massive Semantic Web data compression with MapReduce. in Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010. ACM.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1548616358","https://openalex.org/W1565595968","https://openalex.org/W1578906473","https://openalex.org/W1989009626","https://openalex.org/W2016576449","https://openalex.org/W2076747312","https://openalex.org/W2098935637","https://openalex.org/W2099052309","https://openalex.org/W2110086534","https://openalex.org/W2121310846","https://openalex.org/W2135577024","https://openalex.org/W2140613126","https://openalex.org/W2154894831","https://openalex.org/W2167211997","https://openalex.org/W2173213060","https://openalex.org/W4239696231","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2366430559","https://openalex.org/W2349698472","https://openalex.org/W1585941060","https://openalex.org/W2355823470","https://openalex.org/W1985801232","https://openalex.org/W1710908466","https://openalex.org/W2005492920","https://openalex.org/W1975429881","https://openalex.org/W1560244990","https://openalex.org/W4211114681"],"abstract_inverted_index":{"The":[0,94],"Semantic":[1,74],"Web":[2,75],"consists":[3],"of":[4,7,10,23,26,46,73,91,108,121],"many":[5],"billions":[6],"statements":[8],"made":[9],"terms":[11,20],"that":[12,65,97,111],"are":[13],"either":[14],"URIs":[15],"or":[16],"literals.":[17],"Since":[18],"these":[19],"usually":[21],"consist":[22],"long":[24],"sequences":[25],"characters,":[27],"an":[28,89],"effective":[29],"compression":[30,53],"technique":[31],"must":[32],"be":[33],"used":[34],"to":[35,102],"reduce":[36],"the":[37,42,47,83,92,116],"data":[38,52,109],"size":[39,118],"and":[40,68,86,110,119],"increase":[41],"application":[43],"performance.":[44,93],"One":[45],"best":[48],"known":[49],"techniques":[50],"for":[51],"is":[54,100],"dictionary":[55],"encoding.":[56],"In":[57],"this":[58],"paper":[59],"we":[60,87],"propose":[61],"a":[62,70,80,105],"MapReduce":[63],"algorithm":[64],"efficiently":[66,103],"compresses":[67],"decompresses":[69],"large":[71,106],"amount":[72,107],"data.":[76],"We":[77],"have":[78],"implemented":[79],"prototype":[81],"using":[82],"Hadoop":[84],"framework":[85],"report":[88],"evaluation":[90,95],"shows":[96],"our":[98],"approach":[99],"able":[101],"compress":[104],"it":[112],"scales":[113],"linearly":[114],"regarding":[115],"input":[117],"number":[120],"nodes.":[122]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
