{"id":"https://openalex.org/W4389370967","doi":"https://doi.org/10.1109/taslp.2023.3337633","title":"Datastore Distillation for Nearest Neighbor Machine Translation","display_name":"Datastore Distillation for Nearest Neighbor Machine Translation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389370967","doi":"https://doi.org/10.1109/taslp.2023.3337633"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3337633","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3337633","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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/A5103136822","display_name":"Yuhan Dai","orcid":"https://orcid.org/0000-0002-4623-6612"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhan Dai","raw_affiliation_strings":["Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028604823","display_name":"Zhirui Zhang","orcid":"https://orcid.org/0000-0003-1385-3742"},"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":"Zhirui Zhang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058580034","display_name":"Yichao Du","orcid":"https://orcid.org/0009-0003-6646-7447"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichao Du","raw_affiliation_strings":["Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047453825","display_name":"Shengcai Liu","orcid":"https://orcid.org/0000-0002-4223-2438"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengcai Liu","raw_affiliation_strings":["Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005411806","display_name":"Lemao Liu","orcid":"https://orcid.org/0000-0003-3804-5768"},"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":"Lemao Liu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Big Data Analysis and Application, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103136822"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16248969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"807","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7305071353912354},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5548064112663269},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5507272481918335},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5493653416633606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4822590947151184},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.47326019406318665},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4605731964111328},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45490890741348267},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.453037828207016},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4485793709754944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43313130736351013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33376845717430115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17116275429725647},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16002577543258667},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08392369747161865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305071353912354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5548064112663269},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5507272481918335},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5493653416633606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4822590947151184},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.47326019406318665},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4605731964111328},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45490890741348267},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.453037828207016},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4485793709754944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43313130736351013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33376845717430115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17116275429725647},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16002577543258667},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08392369747161865},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3337633","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3337633","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3604000827","display_name":null,"funder_award_id":"62222213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4442529403","display_name":null,"funder_award_id":"U22B2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7295420491","display_name":null,"funder_award_id":"62072423","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1902237438","https://openalex.org/W2021302824","https://openalex.org/W2101105183","https://openalex.org/W2794365787","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2963506925","https://openalex.org/W2970295111","https://openalex.org/W2970678329","https://openalex.org/W2998702515","https://openalex.org/W3007672467","https://openalex.org/W3126880001","https://openalex.org/W3134891661","https://openalex.org/W3170427498","https://openalex.org/W3175863856","https://openalex.org/W3199147803","https://openalex.org/W3200230461","https://openalex.org/W4205694376","https://openalex.org/W4225388806","https://openalex.org/W4226107280","https://openalex.org/W4230252363","https://openalex.org/W4285170631","https://openalex.org/W4285224675","https://openalex.org/W4301368689","https://openalex.org/W4385571506","https://openalex.org/W4385571663","https://openalex.org/W4385572987","https://openalex.org/W4385573113","https://openalex.org/W4389519303","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6727099177","https://openalex.org/W6729053843","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6749740488","https://openalex.org/W6754905691","https://openalex.org/W6765069029","https://openalex.org/W6770813465","https://openalex.org/W6774222543","https://openalex.org/W6777615688","https://openalex.org/W6779872132","https://openalex.org/W6783813245","https://openalex.org/W6789787868","https://openalex.org/W6810384513","https://openalex.org/W6850257961","https://openalex.org/W6850566649"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2949968076","https://openalex.org/W2935811960","https://openalex.org/W2969407538"],"abstract_inverted_index":{"Nearest":[0],"neighbor":[1,28,101],"machine":[2,21],"translation":[3,15,22],"(i.e.,":[4],"<inline-formula":[5,34,48],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[6,35,49],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[7,36,50],"notation=\"LaTeX\">$k$</tex-math></inline-formula>NN-MT)":[8],"is":[9,86],"a":[10,74,89,96,147],"promising":[11],"approach":[12,124],"to":[13,42,52,77,109,135],"enhance":[14],"quality":[16],"by":[17,66,82,133,146],"equipping":[18],"pre-trained":[19],"neural":[20],"(NMT)":[23],"models":[24],"with":[25],"the":[26,67,79,105,128,131,151,162,168],"nearest":[27,100],"retrieval.":[29],"Despite":[30],"its":[31,44],"great":[32],"success,":[33],"notation=\"LaTeX\">$k$</tex-math></inline-formula>NN-MT":[37,51],"typically":[38],"requires":[39],"ample":[40],"space":[41],"store":[43],"token-level":[45],"datastore,":[46],"causing":[47],"be":[53],"less":[54],"practical":[55],"in":[56,167],"edge":[57],"devices":[58],"or":[59],"online":[60],"scenarios.":[61],"In":[62],"this":[63],"paper,":[64],"inspired":[65],"concept":[68],"of":[69,130,164],"knowledge":[70],"distillation,":[71,84],"we":[72],"provide":[73],"new":[75],"perspective":[76],"ease":[78],"storage":[80],"overhead":[81],"datastore":[83,106,132],"which":[85],"formalized":[87],"as":[88],"constrained":[90],"optimization":[91],"problem.":[92],"We":[93],"further":[94,160],"design":[95],"novel":[97],"model-agnostic":[98],"iterative":[99],"merging":[102],"method":[103,166],"for":[104],"distillation":[107],"problem":[108],"obtain":[110],"an":[111],"effective":[112],"and":[113],"efficient":[114],"solution.":[115],"Experiments":[116],"on":[117,158],"three":[118],"benchmark":[119],"datasets":[120],"indicate":[121],"that":[122],"our":[123,165],"not":[125],"only":[126],"reduces":[127],"volume":[129],"up":[134],"50%":[136],"without":[137],"significant":[138],"performance":[139],"degradation,":[140],"but":[141],"also":[142],"outperforms":[143],"other":[144],"baselines":[145],"large":[148],"margin":[149],"at":[150],"same":[152],"compression":[153],"rate.":[154],"Another":[155],"experiment":[156],"conducted":[157],"WikiText-103":[159],"demonstrates":[161],"effectiveness":[163],"language":[169],"model":[170],"task.":[171]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}