{"id":"https://openalex.org/W2904269425","doi":"https://doi.org/10.1145/3289600.3291011","title":"Asynchronous Training of Word Embeddings for Large Text Corpora","display_name":"Asynchronous Training of Word Embeddings for Large Text Corpora","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2904269425","doi":"https://doi.org/10.1145/3289600.3291011","mag":"2904269425"},"language":"en","primary_location":{"id":"doi:10.1145/3289600.3291011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3291011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.03825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Avishek Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Avishek Anand","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Megha Khosla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Megha Khosla","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaspreet Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jaspreet Singh","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jan-Hendrik Zab","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan-Hendrik Zab","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zijian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136150"],"apc_list":null,"apc_paid":null,"fwci":0.2819,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63253316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"176"},"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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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/scalability","display_name":"Scalability","score":0.6496999859809875},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.599399983882904},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5054000020027161},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4390999972820282},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8737000226974487},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6496999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6279000043869019},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5889999866485596},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3289600.3291011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3291011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.03825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03825","pdf_url":"https://arxiv.org/pdf/1812.03825","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.03825","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03825","pdf_url":"https://arxiv.org/pdf/1812.03825","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W29354635","https://openalex.org/W1443099000","https://openalex.org/W2032618685","https://openalex.org/W2057069782","https://openalex.org/W2067438047","https://openalex.org/W2080100102","https://openalex.org/W2098801107","https://openalex.org/W2102458936","https://openalex.org/W2125031621","https://openalex.org/W2138243089","https://openalex.org/W2153579005","https://openalex.org/W2167949727","https://openalex.org/W2185864411","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251939518","https://openalex.org/W2293547632","https://openalex.org/W2294865516","https://openalex.org/W2341132943","https://openalex.org/W2341557172","https://openalex.org/W2510769428","https://openalex.org/W2579247884","https://openalex.org/W2962715821","https://openalex.org/W6687322159","https://openalex.org/W6720058583","https://openalex.org/W6732015709","https://openalex.org/W6747421177"],"related_works":[],"abstract_inverted_index":{"Word":[0],"embeddings":[1,24,77],"are":[2,40,173,181],"a":[3,71,110,119,144],"powerful":[4],"approach":[5,73],"for":[6,45],"analyzing":[7],"language":[8],"and":[9,20,38,58,131,135,180],"have":[10,49],"been":[11,50],"widely":[12],"popular":[13],"in":[14,17,84,118,143,178],"numerous":[15],"tasks":[16],"information":[18],"retrieval":[19],"text":[21,90],"mining.":[22],"Training":[23],"over":[25],"huge":[26],"corpora":[27,91],"is":[28,34],"computationally":[29],"expensive":[30,63],"because":[31],"the":[32,80,95,98,160,164],"input":[33,81],"typically":[35,116],"sequentially":[36],"processed":[37],"parameters":[39],"synchronously":[41],"updated.":[42],"Distributed":[43],"architectures":[44],"asynchronous":[46],"training":[47,101,124],"that":[48,115,171],"proposed":[51],"either":[52],"focus":[53],"on":[54],"scaling":[55],"vocabulary":[56],"sizes":[57,130],"dimensionality":[59],"or":[60],"suffer":[61],"from":[62],"synchronization":[64,108],"latencies.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,132,168,172],"propose":[70],"scalable":[72],"to":[74,86,88,127,139,175,183],"train":[75],"word":[76,186],"by":[78,152,163],"partitioning":[79],"space":[82],"instead":[83],"order":[85],"scale":[87],"massive":[89],"while":[92],"not":[93,104],"sacrificing":[94],"performance":[96,141],"of":[97,146,159],"embeddings.":[99],"Our":[100,122],"procedure":[102,155],"does":[103],"involve":[105],"any":[106],"parameter":[107],"except":[109],"final":[111],"sub-model":[112],"merge":[113],"phase":[114],"executes":[117],"few":[120],"minutes.":[121],"distributed":[123,154],"scales":[125],"seamlessly":[126],"large":[128],"corpus":[129],"get":[133],"comparable":[134],"sometimes":[136],"even":[137],"up":[138],"45%":[140],"improvement":[142],"variety":[145],"NLP":[147],"benchmarks":[148],"using":[149],"models":[150],"trained":[151],"our":[153],"which":[156],"requires":[157],"$1/10$":[158],"time":[161],"taken":[162],"baseline":[165],"approach.":[166],"Finally":[167],"also":[169],"show":[170],"robust":[174],"missing":[176],"words":[177],"sub-models":[179],"able":[182],"effectively":[184],"reconstruct":[185],"representations.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2018-12-22T00:00:00"}