{"id":"https://openalex.org/W2170036644","doi":"https://doi.org/10.1145/2452376.2452389","title":"Computing n-gram statistics in MapReduce","display_name":"Computing n-gram statistics in MapReduce","publication_year":2013,"publication_date":"2013-03-18","ids":{"openalex":"https://openalex.org/W2170036644","doi":"https://doi.org/10.1145/2452376.2452389","mag":"2170036644"},"language":"en","primary_location":{"id":"doi:10.1145/2452376.2452389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5039440854","display_name":"Klaus Berberich","orcid":"https://orcid.org/0000-0003-3813-9721"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Berberich","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085995102","display_name":"Srikanta Bedathur","orcid":"https://orcid.org/0000-0002-3949-2175"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srikanta Bedathur","raw_affiliation_strings":["Indraprastha Institute of Information Technology, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, New Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5231,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.93950862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.8087558150291443},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.7186466455459595},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.700138509273529},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6514087915420532},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6473570466041565},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5435263514518738},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5398563146591187},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4332963824272156},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4219488501548767},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.4172726273536682},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3722638487815857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2752857208251953},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23061132431030273},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.1714908480644226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12664449214935303},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12623199820518494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087558150291443},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.7186466455459595},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.700138509273529},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6514087915420532},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6473570466041565},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5435263514518738},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5398563146591187},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4332963824272156},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4219488501548767},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.4172726273536682},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3722638487815857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2752857208251953},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23061132431030273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.1714908480644226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12664449214935303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12623199820518494},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2452376.2452389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W67447785","https://openalex.org/W1492896593","https://openalex.org/W1506285740","https://openalex.org/W1529075208","https://openalex.org/W1573197814","https://openalex.org/W1598064945","https://openalex.org/W1608194207","https://openalex.org/W1631260214","https://openalex.org/W1641039719","https://openalex.org/W1998024002","https://openalex.org/W2008434289","https://openalex.org/W2019096529","https://openalex.org/W2025122101","https://openalex.org/W2056910091","https://openalex.org/W2061601738","https://openalex.org/W2062028408","https://openalex.org/W2076489648","https://openalex.org/W2109664771","https://openalex.org/W2110893883","https://openalex.org/W2115482638","https://openalex.org/W2116440993","https://openalex.org/W2120101509","https://openalex.org/W2126399065","https://openalex.org/W2134237567","https://openalex.org/W2137548844","https://openalex.org/W2145833060","https://openalex.org/W2146606092","https://openalex.org/W2148372359","https://openalex.org/W2154507487","https://openalex.org/W2158454296","https://openalex.org/W2158874082","https://openalex.org/W2160484851","https://openalex.org/W2166559705","https://openalex.org/W2166951489","https://openalex.org/W2168196587","https://openalex.org/W2168859760","https://openalex.org/W2169615869","https://openalex.org/W2173213060","https://openalex.org/W2293888039","https://openalex.org/W2621280964","https://openalex.org/W6636811518","https://openalex.org/W6684971642"],"related_works":["https://openalex.org/W2809748609","https://openalex.org/W3033694952","https://openalex.org/W2372558933","https://openalex.org/W2349288944","https://openalex.org/W2085265870","https://openalex.org/W797244100","https://openalex.org/W1999431223","https://openalex.org/W2043772124","https://openalex.org/W2801186172","https://openalex.org/W2367560286"],"abstract_inverted_index":{"Statistics":[0],"about":[1],"n-grams":[2],"(i.e.,":[3],"sequences":[4],"of":[5,67,93,100,123,143],"contiguous":[6],"words":[7],"or":[8,14],"other":[9,15],"tokens":[10],"in":[11,23],"text":[12],"documents":[13],"string":[16],"data)":[17],"are":[18],"an":[19,65,120],"important":[20],"building":[21],"block":[22],"information":[24],"retrieval":[25],"and":[26,45,86,102,135,141],"natural":[27],"language":[28],"processing.":[29,58],"In":[30],"this":[31],"work,":[32],"we":[33,116],"study":[34],"how":[35],"n-gram":[36,43],"statistics,":[37],"optionally":[38],"restricted":[39],"by":[40],"a":[41,78,112],"maximum":[42],"length":[44],"minimum":[46],"collection":[47],"frequency,":[48],"can":[49],"be":[50],"computed":[51],"efficiently":[52],"harnessing":[53],"MapReduce":[54],"for":[55],"distributed":[56],"data":[57],"We":[59,89],"describe":[60],"different":[61],"algorithms,":[62],"ranging":[63],"from":[64],"extension":[66],"word":[68],"counting,":[69],"via":[70],"methods":[71],"based":[72],"on":[73,84,119,128],"the":[74,98,124,138,144],"Apriori":[75],"principle,":[76],"to":[77,96,103],"novel":[79],"method":[80,95],"Suffix-\u03c3":[81],"that":[82],"relies":[83],"sorting":[85],"aggregating":[87],"suffixes.":[88],"examine":[90],"possible":[91],"extensions":[92],"our":[94],"support":[97],"notions":[99],"maximality/closedness":[101],"perform":[104],"aggregations":[105],"beyond":[106],"occurrence":[107],"counting.":[108],"Assuming":[109],"Hadoop":[110],"as":[111],"concrete":[113],"Map-Reduce":[114],"implementation,":[115],"provide":[117],"insights":[118],"efficient":[121],"implementation":[122],"methods.":[125,145],"Extensive":[126],"experiments":[127],"The":[129],"New":[130],"York":[131],"Times":[132],"Annotated":[133],"Corpus":[134],"ClueWeb09":[136],"expose":[137],"relative":[139],"benefits":[140],"trade-offs":[142]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
