{"id":"https://openalex.org/W3194884147","doi":"https://doi.org/10.1145/3447548.3470791","title":"Language Scaling","display_name":"Language Scaling","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3194884147","doi":"https://doi.org/10.1145/3447548.3470791","mag":"3194884147"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3470791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3470791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5077262995","display_name":"Linjun Shou","orcid":"https://orcid.org/0000-0002-1050-7708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjun Shou","raw_affiliation_strings":["Microsoft STCA NLP Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640051","display_name":"Ming Gong","orcid":"https://orcid.org/0000-0001-6140-7187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Gong","raw_affiliation_strings":["Microsoft STCA NLP Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Simon Fraser University, British Columbia, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, British Columbia, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiubo Geng","raw_affiliation_strings":["Microsoft STCA NLP Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012002919","display_name":"Xingjie Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjie Zhou","raw_affiliation_strings":["Microsoft STCA NLP Group, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group, Suzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["Microsoft STCA NLP Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA NLP Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4068","last_page":"4069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9980999827384949,"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":0.8212661147117615},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.7056903839111328},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.561612606048584},{"id":"https://openalex.org/keywords/pragmatics","display_name":"Pragmatics","score":0.5452166795730591},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5026042461395264},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49445343017578125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4296151399612427},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.376231849193573},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23287785053253174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212661147117615},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7056903839111328},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.561612606048584},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.5452166795730591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5026042461395264},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49445343017578125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4296151399612427},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.376231849193573},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23287785053253174},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3470791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3470791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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":23,"referenced_works":["https://openalex.org/W2152691628","https://openalex.org/W2250741688","https://openalex.org/W2258701653","https://openalex.org/W2308486447","https://openalex.org/W2948335087","https://openalex.org/W2952289666","https://openalex.org/W2963881719","https://openalex.org/W2981770024","https://openalex.org/W2994636820","https://openalex.org/W2998653236","https://openalex.org/W3014467241","https://openalex.org/W3021663125","https://openalex.org/W3021762813","https://openalex.org/W3034467872","https://openalex.org/W3034708897","https://openalex.org/W3034724424","https://openalex.org/W3085479580","https://openalex.org/W3093517588","https://openalex.org/W3097294332","https://openalex.org/W3100889051","https://openalex.org/W3102135593","https://openalex.org/W3107826490","https://openalex.org/W3114463723"],"related_works":["https://openalex.org/W1898246925","https://openalex.org/W2375878451","https://openalex.org/W4254159134","https://openalex.org/W4385582530","https://openalex.org/W1535074856","https://openalex.org/W2359993012","https://openalex.org/W2903036871","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Language":[0,6,17],"scaling":[1,18,40,89],"aims":[2],"to":[3,29,33,44,57,106,119,133],"deploy":[4,30],"Natural":[5],"Processing":[7],"(NLP)":[8],"applications":[9,43],"economically":[10],"across":[11],"many":[12,26],"countries/regions":[13],"with":[14,82],"different":[15,68],"languages.":[16,69],"has":[19],"been":[20],"heavily":[21],"invested":[22],"by":[23],"industry":[24],"since":[25],"parties":[27],"want":[28],"their":[31],"applications/services":[32],"global":[34],"markets.":[35],"At":[36],"the":[37,58,62,95,129],"same":[38],"time,":[39],"out":[41],"NLP":[42,138],"various":[45,121,135],"languages,":[46],"essentially":[47],"a":[48,53,72,83,117],"data":[49,113],"science":[50],"problem,":[51],"remains":[52],"grand":[54],"challenge":[55],"due":[56],"huge":[59],"differences":[60],"in":[61,123,146],"morphology,":[63],"syntaxes,":[64],"and":[65,75,90,112,149],"pragmatics":[66],"among":[67],"We":[70,80,115],"present":[71,116],"comprehensive":[73],"survey":[74],"tutorial":[76,130],"on":[77,94],"language":[78,88,107],"scaling.":[79],"start":[81],"clear":[84],"problem":[85],"description":[86],"for":[87],"an":[91],"intuitive":[92],"discussion":[93],"overall":[96],"challenges.":[97],"Then,":[98],"we":[99,141],"outline":[100],"two":[101],"major":[102],"categories":[103],"of":[104,128,137],"approaches":[105],"scaling,":[108],"namely,":[109],"model":[110],"transfer":[111],"transfer.":[114],"taxonomy":[118],"summarize":[120],"methods":[122],"literature.":[124],"A":[125],"large":[126],"part":[127],"is":[131],"organized":[132],"address":[134],"types":[136],"applications.":[139],"Finally,":[140],"discuss":[142],"several":[143],"important":[144],"challenges":[145],"this":[147],"area":[148],"future":[150],"directions.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-08-30T00:00:00"}