{"id":"https://openalex.org/W2633911929","doi":"https://doi.org/10.18653/v1/w17-3208","title":"An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation","display_name":"An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2633911929","doi":"https://doi.org/10.18653/v1/w17-3208","mag":"2633911929"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-3208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3208","pdf_url":"https://www.aclweb.org/anthology/W17-3208.pdf","source":null,"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 First Workshop on Neural Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-3208.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056547537","display_name":"Makoto Morishita","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Makoto Morishita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075065777","display_name":"Yusuke Oda","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Oda","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University","Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","raw_affiliation_strings":["Nara Institute of Science and Technology","PRESTO, Japan Science and Technology Agency"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"PRESTO, Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhito Sudoh","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056547537"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.2864,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90894564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9918000102043152,"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":0.8178821802139282},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.758118748664856},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.7255324125289917},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6557570099830627},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5889285802841187},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5659072399139404},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5167702436447144},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5024833679199219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4662524461746216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45544150471687317},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4447228014469147},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.44238972663879395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40759405493736267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34495463967323303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18649479746818542},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11201906204223633},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08840999007225037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178821802139282},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.758118748664856},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.7255324125289917},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6557570099830627},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5889285802841187},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5659072399139404},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5167702436447144},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5024833679199219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4662524461746216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45544150471687317},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4447228014469147},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.44238972663879395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40759405493736267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34495463967323303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18649479746818542},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11201906204223633},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08840999007225037},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-3208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3208","pdf_url":"https://www.aclweb.org/anthology/W17-3208.pdf","source":null,"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 First Workshop on Neural Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-3208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-3208","pdf_url":"https://www.aclweb.org/anthology/W17-3208.pdf","source":null,"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 First Workshop on Neural Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5194182431","display_name":"Controllable Natural Language Generation with Neural Networks","funder_award_id":"16H05873","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2633911929.pdf","grobid_xml":"https://content.openalex.org/works/W2633911929.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W2101105183","https://openalex.org/W2127863960","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2512924740","https://openalex.org/W2525778437","https://openalex.org/W2573523139","https://openalex.org/W2576482813","https://openalex.org/W2577255746","https://openalex.org/W2594990650","https://openalex.org/W2963212250","https://openalex.org/W2964121744","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W2095055219","https://openalex.org/W2362374543","https://openalex.org/W2116295091","https://openalex.org/W4319430205","https://openalex.org/W3121711078","https://openalex.org/W927337369","https://openalex.org/W3198265738","https://openalex.org/W2348196682","https://openalex.org/W2085265870"],"abstract_inverted_index":{"Training":[0],"of":[1,60,117],"neural":[2],"machine":[3],"translation":[4],"(NMT)":[5],"models":[6],"usually":[7],"uses":[8],"mini-batches":[9,56],"for":[10,38,88],"efficiency":[11],"purposes.":[12],"During":[13],"the":[14,34,47,51,58,64,69,115],"minibatched":[15],"training":[16,128],"process,":[17],"it":[18],"is":[19,74],"necessary":[20],"to":[21,28,33],"pad":[22],"shorter":[23],"sentences":[24],"in":[25,31,78],"a":[26,118,123],"mini-batch":[27,72,102],"be":[29],"equal":[30],"length":[32,53],"longest":[35],"sentence":[36,52],"therein":[37],"efficient":[39],"computation.":[40],"Previous":[41],"work":[42,100,137],"has":[43,122],"noted":[44],"that":[45,71,114],"sorting":[46,132],"corpus":[48],"based":[49],"on":[50,126],"before":[54],"making":[55],"reduces":[57],"amount":[59],"padding":[61],"and":[62,129],"increases":[63],"processing":[65],"speed.":[66],"However,":[67],"despite":[68],"fact":[70],"creation":[73,103,120],"an":[75],"essential":[76],"step":[77],"NMT":[79,83,127],"training,":[80],"widely":[81],"used":[82],"toolkits":[84],"implement":[85],"disparate":[86],"strategies":[87,104,133],"doing":[89],"so,":[90],"which":[91],"have":[92],"not":[93,135],"been":[94],"empirically":[95],"validated":[96],"or":[97],"compared.":[98],"This":[99],"investigates":[101],"with":[105,140],"experiments":[106],"over":[107],"two":[108],"different":[109],"datasets.":[110],"Our":[111],"results":[112],"suggest":[113],"choice":[116],"minibatch":[119],"strategy":[121],"large":[124],"effect":[125],"some":[130],"length-based":[131],"do":[134],"always":[136],"well":[138],"compared":[139],"simple":[141],"shuffling.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}