{"id":"https://openalex.org/W2981467700","doi":"https://doi.org/10.14778/3352063.3352136","title":"A distributed system for large-scale n-gram language models at Tencent","display_name":"A distributed system for large-scale n-gram language models at Tencent","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2981467700","doi":"https://doi.org/10.14778/3352063.3352136","mag":"2981467700"},"language":"en","primary_location":{"id":"doi:10.14778/3352063.3352136","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352136","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5044561539","display_name":"Qiang Long","orcid":"https://orcid.org/0009-0000-9664-0712"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Long","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391896","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1717-5785"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinfu Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfu Deng","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589055","display_name":"Song Liu","orcid":"https://orcid.org/0000-0002-4563-0183"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Liu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562765","display_name":"Wenhao Huang","orcid":"https://orcid.org/0000-0001-7557-1391"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Huang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081534375","display_name":"Fangying Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangying Chen","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070605006","display_name":"Sifan Liu","orcid":"https://orcid.org/0000-0002-1608-4216"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Liu","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4338,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72636778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":"12","first_page":"2206","last_page":"2217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T11478","display_name":"Caching and Content Delivery","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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8492310047149658},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7524278163909912},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6371256113052368},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6105956435203552},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.555189847946167},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5463153123855591},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5211446285247803},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4892082214355469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24947580695152283},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.17470860481262207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10547089576721191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492310047149658},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7524278163909912},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6371256113052368},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6105956435203552},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.555189847946167},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5463153123855591},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5211446285247803},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4892082214355469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24947580695152283},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17470860481262207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10547089576721191},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3352063.3352136","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352136","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W182831726","https://openalex.org/W1710082047","https://openalex.org/W1917432393","https://openalex.org/W1934041838","https://openalex.org/W1991995555","https://openalex.org/W2017708149","https://openalex.org/W2046932483","https://openalex.org/W2102113734","https://openalex.org/W2109664771","https://openalex.org/W2143612262","https://openalex.org/W2158195707","https://openalex.org/W2160815625","https://openalex.org/W2171928131","https://openalex.org/W2175585630","https://openalex.org/W2193413348","https://openalex.org/W2259472270","https://openalex.org/W2266486761","https://openalex.org/W2513992500","https://openalex.org/W2565600385","https://openalex.org/W2613751718","https://openalex.org/W2752236330","https://openalex.org/W2786278116","https://openalex.org/W2799200478","https://openalex.org/W2949640717","https://openalex.org/W2951793508","https://openalex.org/W2964108773","https://openalex.org/W2998704965","https://openalex.org/W6600312833","https://openalex.org/W6603616073","https://openalex.org/W6638218882","https://openalex.org/W6654500195","https://openalex.org/W6676373471","https://openalex.org/W6742629869"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2624072012","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W2084276039","https://openalex.org/W4307474317","https://openalex.org/W2008468404","https://openalex.org/W2147879411","https://openalex.org/W2132221452"],"abstract_inverted_index":{"n-gram":[0,30,121],"language":[1,7],"models":[2,31,122,147],"are":[3],"widely":[4],"used":[5],"in":[6],"processing":[8],"applications,":[9],"e.g.,":[10,25],"automatic":[11,134],"speech":[12,135],"recognition,":[13],"for":[14,85,157],"ranking":[15,35],"the":[16,22,26,48,54,87,98,103,125,128,162,167],"candidate":[17],"word":[18],"sequences":[19],"generated":[20],"from":[21],"generator":[23],"model,":[24],"acoustic":[27],"model.":[28],"Large":[29],"typically":[32],"give":[33],"good":[34],"results;":[36],"however,":[37],"they":[38],"require":[39],"a":[40,60,67,112],"huge":[41],"amount":[42],"of":[43,127,169,172],"memory":[44,55],"storage.":[45],"While":[46],"distributing":[47],"model":[49],"across":[50],"multiple":[51],"nodes":[52],"resolves":[53],"issue,":[56],"it":[57,156],"nonetheless":[58],"incurs":[59],"great":[61],"network":[62,88,99,164],"communication":[63],"overhead":[64],"and":[65,94,101,150],"introduces":[66],"different":[68],"bottleneck.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"present":[74],"our":[75,141],"distributed":[76,91,142],"system":[77,143],"developed":[78],"at":[79,166],"Tencent":[80],"with":[81,161],"novel":[82],"optimization":[83],"techniques":[84],"reducing":[86],"overhead,":[89],"including":[90],"indexing,":[92],"batching":[93],"caching.":[95],"They":[96],"reduce":[97],"requests":[100],"accelerate":[102],"operation":[104],"on":[105,124,132],"each":[106],"single":[107],"node.":[108],"We":[109,152],"also":[110],"propose":[111],"cascade":[113],"fault-tolerance":[114],"mechanism":[115],"which":[116],"adaptively":[117],"switches":[118],"to":[119,145],"small":[120],"depending":[123],"severity":[126],"failure.":[129],"Experimental":[130],"study":[131],"9":[133],"recognition":[136],"(ASR)":[137],"datasets":[138],"confirms":[139],"that":[140],"scales":[144],"large":[146],"efficiently,":[148],"effectively":[149],"robustly.":[151],"have":[153],"successfully":[154],"deployed":[155],"Tencent's":[158],"WeChat":[159],"ASR":[160],"peak":[163],"traffic":[165],"scale":[168],"100":[170],"millions":[171],"messages":[173],"per":[174],"minute.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}