{"id":"https://openalex.org/W4385572987","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.284","title":"Chunk-based Nearest Neighbor Machine Translation","display_name":"Chunk-based Nearest Neighbor Machine Translation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572987","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.284"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.284","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.284","pdf_url":"https://aclanthology.org/2022.emnlp-main.284.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.284.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112974337","display_name":"Pedro Henrique Martins","orcid":"https://orcid.org/0009-0005-8604-8447","observed_orcids":["https://orcid.org/0009-0005-8604-8447"]},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro Henrique Martins","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I4387152517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081932185","display_name":"Zita Marinho","orcid":"https://orcid.org/0000-0002-6314-6096","observed_orcids":["https://orcid.org/0000-0002-6314-6096"]},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Zita Marinho","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I4387152517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051693368","display_name":"Andr\u00e9 F. T. Martins","orcid":"https://orcid.org/0000-0001-6863-4681","observed_orcids":["https://orcid.org/0000-0001-6863-4681"]},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 F. T. Martins","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es Unbabel Institute of Systems and Robotics DeepMind LUMLIS (Lisbon ELLIS Unit), Instituto Superior T\u00e9cnico Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I4387152517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1356,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90729306,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4228","last_page":"4245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9175000190734863,"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":0.9175000190734863,"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":0.07180000096559525,"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":0.005100000184029341,"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/semiparametric-models","display_name":"semiparametric models","score":0.7170000076293945},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.6639999747276306},{"id":"https://openalex.org/keywords/decoding-speed","display_name":"decoding speed","score":0.7099999785423279},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.5619999766349792},{"id":"https://openalex.org/keywords/translation-quality","display_name":"translation quality","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9136295318603516},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7874685525894165},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7333367466926575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5995613932609558},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5668427348136902},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5361032485961914},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5125539302825928},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5105687379837036},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42793548107147217},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4124407172203064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16143912076950073},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.284","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.284","pdf_url":"https://aclanthology.org/2022.emnlp-main.284.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.12230","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.12230","pdf_url":"https://arxiv.org/pdf/2205.12230","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2205.12230","doi":"https://doi.org/10.48550/arxiv.2205.12230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.12230","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.284","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.284","pdf_url":"https://aclanthology.org/2022.emnlp-main.284.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2144570049","display_name":null,"funder_award_id":"UIDB/50008","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3375535518","display_name":"Instituto de Telecomunica\u00e7\u00f5es","funder_award_id":"UIDB/50008/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3850789590","display_name":null,"funder_award_id":"50008","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G73864865","display_name":null,"funder_award_id":"101070631","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G7713038420","display_name":null,"funder_award_id":"P2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8451627996","display_name":"Models for Natural Language Generation (provis\u00f3rio)","funder_award_id":"PD/BD/150633/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8718590230","display_name":"Aprendizagem Eficiente e Precisa usando Mecanismos de Aten\u00e7\u00e3o","funder_award_id":"PTDC/CCI-INF/4703/2021","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572987.pdf","grobid_xml":"https://content.openalex.org/works/W4385572987.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W2025772227","https://openalex.org/W2117045850","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2160131015","https://openalex.org/W2251000325","https://openalex.org/W2593864460","https://openalex.org/W2626778328","https://openalex.org/W2757592053","https://openalex.org/W2788330850","https://openalex.org/W2798362442","https://openalex.org/W2890810021","https://openalex.org/W2920195923","https://openalex.org/W2933138175","https://openalex.org/W2963506925","https://openalex.org/W2963829526","https://openalex.org/W2970295111","https://openalex.org/W2970925270","https://openalex.org/W2988841832","https://openalex.org/W3014390292","https://openalex.org/W3027879771","https://openalex.org/W3039017601","https://openalex.org/W3087597081","https://openalex.org/W3090145300","https://openalex.org/W3116179216","https://openalex.org/W3134891661","https://openalex.org/W3153411045","https://openalex.org/W3157700644","https://openalex.org/W3175374354","https://openalex.org/W3175863856","https://openalex.org/W3200074555","https://openalex.org/W3200230461","https://openalex.org/W3213851426","https://openalex.org/W4221155916","https://openalex.org/W4226082499","https://openalex.org/W4226107280","https://openalex.org/W4285170631","https://openalex.org/W4287694131","https://openalex.org/W4293088443"],"related_works":["https://openalex.org/W4285224675","https://openalex.org/W3090145300","https://openalex.org/W4321855134","https://openalex.org/W4402670861","https://openalex.org/W4224878982","https://openalex.org/W4393390072","https://openalex.org/W4285170631","https://openalex.org/W3165612646","https://openalex.org/W4399659184","https://openalex.org/W4226107280"],"abstract_inverted_index":{"Semi-parametric":[0],"models,":[1],"which":[2,86,117],"augment":[3],"generation":[4,109],"with":[5,153],"retrieval,":[6],"have":[7],"led":[8],"to":[9,19,22,64,121,146,150],"impressive":[10],"results":[11],"in":[12,125,131,158],"language":[13],"modeling":[14],"and":[15,111,135],"machine":[16,129],"translation,":[17],"due":[18],"their":[20],"ability":[21],"retrieve":[23],"fine-grained":[24],"information":[25],"from":[26,45,91],"a":[27,65,75,82,96,155],"datastore":[28],"of":[29,31,89,95],"examples.One":[30],"the":[32,92,104,108,114,118,126,141],"most":[33],"prominent":[34],"approaches,":[35],"kNN-MT,":[36],"exhibits":[37],"strong":[38],"domain":[39,137],"adaptation":[40],"capabilities":[41],"by":[42],"retrieving":[43],"tokens":[44,90],"domain-specific":[46],"datastores":[47],"(Khandelwal":[48],"et":[49],"al.,":[50],"2021).However,":[51],"kNN-MT":[52,84,143],"requires":[53],"an":[54],"expensive":[55],"retrieval":[56],"operation":[57],"for":[58,102,112,123],"every":[59],"single":[60,97],"generated":[61],"token,":[62],"leading":[63],"very":[66],"low":[67],"decoding":[68],"speed":[69],"(around":[70],"8":[71],"times":[72],"slower":[73],"than":[74],"parametric":[76],"model).In":[77],"this":[78],"paper,":[79],"we":[80],"introduce":[81],"chunk-based":[83,142],"model":[85,119,144],"retrieves":[87],"chunks":[88,106],"datastore,":[93],"instead":[94],"token.We":[98],"propose":[99],"several":[100],"strategies":[101],"incorporating":[103],"retrieved":[105],"into":[107],"process,":[110],"selecting":[113],"steps":[115],"at":[116],"needs":[120],"search":[122],"neighbors":[124],"datastore.Experiments":[127],"on":[128],"translation":[130,159],"two":[132],"settings,":[133],"static":[134],"\"on-the-fly\"":[136],"adaptation,":[138],"show":[139],"that":[140],"leads":[145],"significant":[147],"speed-ups":[148],"(up":[149],"4":[151],"times)":[152],"only":[154],"small":[156],"drop":[157],"quality.":[160],"1":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-05T00:00:00"}