{"id":"https://openalex.org/W4211012425","doi":"https://doi.org/10.2200/s00274ed1v01y201006hlt007","title":"Data-Intensive Text Processing with MapReduce","display_name":"Data-Intensive Text Processing with MapReduce","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W4211012425","doi":"https://doi.org/10.2200/s00274ed1v01y201006hlt007"},"language":"en","primary_location":{"id":"doi:10.2200/s00274ed1v01y201006hlt007","is_oa":true,"landing_page_url":"https://doi.org/10.2200/s00274ed1v01y201006hlt007","pdf_url":"https://www.morganclaypool.com/doi/pdf/10.2200/S00274ED1V01Y201006HLT007","source":{"id":"https://openalex.org/S4210203380","display_name":"Synthesis lectures on human language technologies","issn_l":"1947-4040","issn":["1947-4040","1947-4059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322570","host_organization_name":"Morgan & Claypool Publishers","host_organization_lineage":["https://openalex.org/P4310322570"],"host_organization_lineage_names":["Morgan & Claypool Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Synthesis Lectures on Human Language Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.morganclaypool.com/doi/pdf/10.2200/S00274ED1V01Y201006HLT007","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111222692","display_name":"Chris Dyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Dyer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082997975"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.9929,"has_fulltext":false,"cited_by_count":221,"citation_normalized_percentile":{"value":0.9975802,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9926000237464905,"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":0.8782775402069092},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6905260682106018},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.6351656317710876},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5170974731445312},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.47180309891700745},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4632851481437683},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4452197551727295},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4371177852153778},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4206174910068512},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.41261589527130127},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.28573793172836304},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2491350769996643},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19188013672828674},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.17853042483329773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17211505770683289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782775402069092},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6905260682106018},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.6351656317710876},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5170974731445312},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.47180309891700745},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4632851481437683},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4452197551727295},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4371177852153778},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4206174910068512},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.41261589527130127},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.28573793172836304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2491350769996643},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19188013672828674},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.17853042483329773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17211505770683289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2200/s00274ed1v01y201006hlt007","is_oa":true,"landing_page_url":"https://doi.org/10.2200/s00274ed1v01y201006hlt007","pdf_url":"https://www.morganclaypool.com/doi/pdf/10.2200/S00274ED1V01Y201006HLT007","source":{"id":"https://openalex.org/S4210203380","display_name":"Synthesis lectures on human language technologies","issn_l":"1947-4040","issn":["1947-4040","1947-4059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322570","host_organization_name":"Morgan & Claypool Publishers","host_organization_lineage":["https://openalex.org/P4310322570"],"host_organization_lineage_names":["Morgan & Claypool Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Synthesis Lectures on Human Language Technologies","raw_type":"journal-article"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-030085667","is_oa":false,"landing_page_url":"https://doi.org/10.2200/S00274ED1V01Y201006HLT007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"software, multimedia"}],"best_oa_location":{"id":"doi:10.2200/s00274ed1v01y201006hlt007","is_oa":true,"landing_page_url":"https://doi.org/10.2200/s00274ed1v01y201006hlt007","pdf_url":"https://www.morganclaypool.com/doi/pdf/10.2200/S00274ED1V01Y201006HLT007","source":{"id":"https://openalex.org/S4210203380","display_name":"Synthesis lectures on human language technologies","issn_l":"1947-4040","issn":["1947-4040","1947-4059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322570","host_organization_name":"Morgan & Claypool Publishers","host_organization_lineage":["https://openalex.org/P4310322570"],"host_organization_lineage_names":["Morgan & Claypool Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Synthesis Lectures on Human Language Technologies","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8616234730","display_name":"III: Small: Ivory -- A Hadoop Toolkit for Distributed Text Retrieval","funder_award_id":"0916043","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8921270995","display_name":"Putting the Clouds in Context:   Statistical Machine Translation with MapReduce","funder_award_id":"0836560","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4211012425.pdf","grobid_xml":"https://content.openalex.org/works/W4211012425.grobid-xml"},"referenced_works_count":115,"referenced_works":["https://openalex.org/W1485293642","https://openalex.org/W1492896593","https://openalex.org/W1500474910","https://openalex.org/W1508165687","https://openalex.org/W1528321674","https://openalex.org/W1538652242","https://openalex.org/W1563780964","https://openalex.org/W1574901103","https://openalex.org/W1916559533","https://openalex.org/W1971421925","https://openalex.org/W1977367431","https://openalex.org/W1978680929","https://openalex.org/W1985229168","https://openalex.org/W1987235421","https://openalex.org/W1993003918","https://openalex.org/W1997020216","https://openalex.org/W1999806105","https://openalex.org/W2005373714","https://openalex.org/W2007709031","https://openalex.org/W2008495066","https://openalex.org/W2012753837","https://openalex.org/W2019724001","https://openalex.org/W2022292926","https://openalex.org/W2027211749","https://openalex.org/W2031302834","https://openalex.org/W2032175749","https://openalex.org/W2037072488","https://openalex.org/W2038316281","https://openalex.org/W2038698865","https://openalex.org/W2039976898","https://openalex.org/W2042690899","https://openalex.org/W2042719229","https://openalex.org/W2043724035","https://openalex.org/W2044490410","https://openalex.org/W2045271686","https://openalex.org/W2045675590","https://openalex.org/W2045841536","https://openalex.org/W2046224275","https://openalex.org/W2046833425","https://openalex.org/W2049633694","https://openalex.org/W2051434435","https://openalex.org/W2054584570","https://openalex.org/W2059586463","https://openalex.org/W2060204338","https://openalex.org/W2063435439","https://openalex.org/W2064379477","https://openalex.org/W2072156548","https://openalex.org/W2073965851","https://openalex.org/W2077200369","https://openalex.org/W2095368471","https://openalex.org/W2096703709","https://openalex.org/W2097927681","https://openalex.org/W2098935637","https://openalex.org/W2099685860","https://openalex.org/W2102667697","https://openalex.org/W2103018059","https://openalex.org/W2104644701","https://openalex.org/W2109469951","https://openalex.org/W2110518760","https://openalex.org/W2112090702","https://openalex.org/W2113718594","https://openalex.org/W2114303224","https://openalex.org/W2115081467","https://openalex.org/W2115457697","https://openalex.org/W2118034653","https://openalex.org/W2119714163","https://openalex.org/W2121928206","https://openalex.org/W2122249806","https://openalex.org/W2124637492","https://openalex.org/W2125775320","https://openalex.org/W2125838338","https://openalex.org/W2127797489","https://openalex.org/W2129817042","https://openalex.org/W2133473621","https://openalex.org/W2134807578","https://openalex.org/W2135052239","https://openalex.org/W2137398441","https://openalex.org/W2138621811","https://openalex.org/W2140919237","https://openalex.org/W2146231755","https://openalex.org/W2147057843","https://openalex.org/W2150871235","https://openalex.org/W2153233077","https://openalex.org/W2153653739","https://openalex.org/W2154894831","https://openalex.org/W2156515921","https://openalex.org/W2156985047","https://openalex.org/W2157355837","https://openalex.org/W2157963512","https://openalex.org/W2167927436","https://openalex.org/W2169533279","https://openalex.org/W2171458318","https://openalex.org/W2173213060","https://openalex.org/W2293888960","https://openalex.org/W2439017901","https://openalex.org/W2616754551","https://openalex.org/W2752885492","https://openalex.org/W2911388033","https://openalex.org/W3083016522","https://openalex.org/W3083239436","https://openalex.org/W3162803548","https://openalex.org/W4205184193","https://openalex.org/W4213009331","https://openalex.org/W4213146104","https://openalex.org/W4230805115","https://openalex.org/W4238584892","https://openalex.org/W4238594802","https://openalex.org/W4238675359","https://openalex.org/W4239429564","https://openalex.org/W4241850027","https://openalex.org/W4244704438","https://openalex.org/W4245854791","https://openalex.org/W4249823756","https://openalex.org/W4251681643","https://openalex.org/W6959643953"],"related_works":["https://openalex.org/W2353464440","https://openalex.org/W3147391527","https://openalex.org/W2158030964","https://openalex.org/W2127197365","https://openalex.org/W2911620088","https://openalex.org/W3133966128","https://openalex.org/W2143942086","https://openalex.org/W3197931669","https://openalex.org/W2125301708","https://openalex.org/W2365666822"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":43},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":26}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}