{"id":"https://openalex.org/W2954548380","doi":"https://doi.org/10.1007/s41019-019-0096-6","title":"Scaling Word2Vec on Big Corpus","display_name":"Scaling Word2Vec on Big Corpus","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2954548380","doi":"https://doi.org/10.1007/s41019-019-0096-6","mag":"2954548380"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-019-0096-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-0096-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-0096-6.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-0096-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080243049","display_name":"Bofang Li","orcid":"https://orcid.org/0009-0000-9723-2999"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Bofang Li","raw_affiliation_strings":["Renmin University of China, Beijing, China","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277099","display_name":"Aleksandr Drozd","orcid":"https://orcid.org/0000-0002-4575-7213"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aleksandr Drozd","raw_affiliation_strings":["AIST-Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory, Tokyo, Japan","RIKEN Center for Computational Science, Kobe, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST-Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017118310","display_name":"Yuhe Guo","orcid":"https://orcid.org/0009-0009-0065-418X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhe Guo","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101983989","display_name":"Tao Liu","orcid":"https://orcid.org/0009-0000-6141-3472"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008721449","display_name":"Xiaoyong Du","orcid":"https://orcid.org/0000-0002-5757-9135"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyong Du","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008721449"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":5.7888,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96768383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"4","issue":"2","first_page":"157","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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/word2vec","display_name":"Word2vec","score":0.822406530380249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852925062179565},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6929574012756348},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4415457844734192},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4396970570087433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35606348514556885},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21051353216171265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07721245288848877}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.822406530380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852925062179565},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6929574012756348},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4415457844734192},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4396970570087433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35606348514556885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21051353216171265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07721245288848877},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41019-019-0096-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-0096-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-0096-6.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4daf56761204571adb845a16bd33f18","is_oa":true,"landing_page_url":"https://doaj.org/article/c4daf56761204571adb845a16bd33f18","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 4, Iss 2, Pp 157-175 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41019-019-0096-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-019-0096-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-019-0096-6.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2428490243","display_name":null,"funder_award_id":"U1711262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G45834996","display_name":null,"funder_award_id":"JPMJCR1687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8549263564","display_name":null,"funder_award_id":"JP17K12739","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G988839521","display_name":"\u57fa\u4e8e\u8bcd\u5411\u91cf\u8868\u793a\u7684\u5927\u89c4\u6a21\u77e5\u8bc6\u56fe\u8c31\u6784\u5efa\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61472428","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954548380.pdf","grobid_xml":"https://content.openalex.org/works/W2954548380.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1615991656","https://openalex.org/W1736726159","https://openalex.org/W1832693441","https://openalex.org/W1854884267","https://openalex.org/W2006672970","https://openalex.org/W2009797711","https://openalex.org/W2026487812","https://openalex.org/W2067438047","https://openalex.org/W2114524997","https://openalex.org/W2117065474","https://openalex.org/W2117130368","https://openalex.org/W2125031621","https://openalex.org/W2128200071","https://openalex.org/W2132166724","https://openalex.org/W2137735870","https://openalex.org/W2140480387","https://openalex.org/W2141599568","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2163455955","https://openalex.org/W2163605009","https://openalex.org/W2170682101","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251771443","https://openalex.org/W2251803266","https://openalex.org/W2293502436","https://openalex.org/W2460442863","https://openalex.org/W2493916176","https://openalex.org/W2507974895","https://openalex.org/W2508434770","https://openalex.org/W2524917517","https://openalex.org/W2572487292","https://openalex.org/W2617242334","https://openalex.org/W2759280239","https://openalex.org/W2765650793","https://openalex.org/W2807036468","https://openalex.org/W2882319491","https://openalex.org/W2912811302","https://openalex.org/W2950577311","https://openalex.org/W2963288913","https://openalex.org/W2963292194","https://openalex.org/W4247704254","https://openalex.org/W4285719527","https://openalex.org/W6601323341","https://openalex.org/W6602287985","https://openalex.org/W6851816929"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2731626691","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084"],"abstract_inverted_index":{"Word":[0],"embedding":[1],"has":[2],"been":[3],"well":[4],"accepted":[5],"as":[6,181],"an":[7],"important":[8],"feature":[9],"in":[10,30],"the":[11,19,104,111,122,127],"area":[12],"of":[13,36,81,129,145],"natural":[14],"language":[15],"processing":[16],"(NLP).":[17],"Specifically,":[18],"Word2Vec":[20,37,57,178],"model":[21,154],"learns":[22],"high-quality":[23],"word":[24,92],"embeddings":[25],"and":[26,93,107,131,134,185],"is":[27,38,68],"widely":[28],"used":[29],"various":[31],"NLP":[32,146],"tasks.":[33,147],"The":[34,148],"training":[35,74,123],"sequential":[39],"on":[40,58,110,160],"a":[41,59,72,79,90,94,143,156],"CPU":[42],"due":[43],"to":[44,55,114],"strong":[45],"dependencies":[46,70],"between":[47],"word\u2013context":[48,87],"pairs.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,102,174],"target":[54],"scale":[56],"GPU":[60],"cluster.":[61],"To":[62],"do":[63],"this,":[64],"one":[65],"main":[66],"challenge":[67],"reducing":[69],"inside":[71],"large":[73],"batch.":[75],"We":[76,138],"heuristically":[77],"design":[78],"variation":[80,118],"Word2Vec,":[82],"which":[83],"ensures":[84],"that":[85,151],"each":[86],"pair":[88],"contains":[89],"non-dependent":[91,112],"uniformly":[95],"sampled":[96],"contextual":[97],"word.":[98],"During":[99],"batch":[100],"training,":[101],"\u201cfreeze\u201d":[103],"context":[105],"part":[106,113],"update":[108],"only":[109],"reduce":[115],"conflicts.":[116],"This":[117],"also":[119],"directly":[120],"controls":[121],"iterations":[124],"by":[125,167],"fixing":[126],"number":[128],"samples":[130],"treats":[132],"high-frequency":[133],"low-frequency":[135],"words":[136],"equally.":[137],"conduct":[139],"extensive":[140],"experiments":[141],"over":[142],"range":[144],"results":[149],"show":[150],"our":[152],"proposed":[153],"achieves":[155,186],"7.5":[157],"times":[158],"acceleration":[159],"16":[161],"GPUs":[162],"without":[163],"accuracy":[164],"drop.":[165],"Moreover,":[166],"using":[168],"high-level":[169],"Chainer":[170],"deep":[171],"learning":[172],"framework,":[173],"can":[175],"easily":[176],"implement":[177],"variations":[179],"such":[180],"CNN-based":[182],"subword-level":[183],"models":[184],"similar":[187],"scaling":[188],"results.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}