{"id":"https://openalex.org/W2980596743","doi":"https://doi.org/10.18653/v1/d19-5625","title":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation","display_name":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2980596743","doi":"https://doi.org/10.18653/v1/d19-5625","mag":"2980596743"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5625","pdf_url":"https://www.aclweb.org/anthology/D19-5625.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 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-5625.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005840801","display_name":"Kenton Murray","orcid":"https://orcid.org/0000-0002-5628-1003"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kenton Murray","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081708301","display_name":"Jeffery Kinnison","orcid":"https://orcid.org/0000-0001-5643-1123"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffery Kinnison","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102874067","display_name":"Toan Nguyen","orcid":"https://orcid.org/0000-0003-2734-0622"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toan Q. Nguyen","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091513740","display_name":"Walter J. Scheirer","orcid":"https://orcid.org/0000-0001-9649-8074"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walter Scheirer","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036026526","display_name":"David Chiang","orcid":"https://orcid.org/0000-0002-0435-4864"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Chiang","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005840801"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67394897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"240"},"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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/machine-translation","display_name":"Machine translation","score":0.7763053178787231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767616868019104},{"id":"https://openalex.org/keywords/sizing","display_name":"Sizing","score":0.7327309846878052},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7221454381942749},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6159989237785339},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5457625985145569},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.525716245174408},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48561444878578186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47935014963150024},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46869492530822754},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4624076187610626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.420171320438385},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1648123860359192},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14436286687850952},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12013795971870422}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7763053178787231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767616868019104},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.7327309846878052},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7221454381942749},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6159989237785339},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5457625985145569},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.525716245174408},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48561444878578186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47935014963150024},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46869492530822754},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4624076187610626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.420171320438385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1648123860359192},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14436286687850952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12013795971870422},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-5625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5625","pdf_url":"https://www.aclweb.org/anthology/D19-5625.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 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.06717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.06717","pdf_url":"https://arxiv.org/pdf/1910.06717","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"},{"id":"mag:2980596743","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.06717v1","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.06717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.06717","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5625","pdf_url":"https://www.aclweb.org/anthology/D19-5625.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 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G8092615179","display_name":null,"funder_award_id":"HR0011-15-C-0115","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980596743.pdf","grobid_xml":"https://content.openalex.org/works/W2980596743.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1928693685","https://openalex.org/W1978259121","https://openalex.org/W1986490585","https://openalex.org/W2047092297","https://openalex.org/W2073515924","https://openalex.org/W2097998348","https://openalex.org/W2098368939","https://openalex.org/W2101105183","https://openalex.org/W2106411961","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2131241448","https://openalex.org/W2143462372","https://openalex.org/W2164278908","https://openalex.org/W2184135559","https://openalex.org/W2395935897","https://openalex.org/W2410082850","https://openalex.org/W2594990650","https://openalex.org/W2796108585","https://openalex.org/W2909951054","https://openalex.org/W2913535645","https://openalex.org/W2917028965","https://openalex.org/W2962784628","https://openalex.org/W2963181996","https://openalex.org/W2963233958","https://openalex.org/W2963347649","https://openalex.org/W2963403868","https://openalex.org/W2963809228","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2986915867","https://openalex.org/W2943847545","https://openalex.org/W3090178526","https://openalex.org/W801523511","https://openalex.org/W3105515454","https://openalex.org/W3094491777","https://openalex.org/W3155904893","https://openalex.org/W3172178920","https://openalex.org/W3055490769","https://openalex.org/W2901508112","https://openalex.org/W1578315993","https://openalex.org/W2915236044","https://openalex.org/W2911072618","https://openalex.org/W2799290373","https://openalex.org/W2952237529","https://openalex.org/W3092746498","https://openalex.org/W3089416163","https://openalex.org/W2943252645","https://openalex.org/W3058788517","https://openalex.org/W2903852246"],"abstract_inverted_index":{"Neural":[0],"sequence-to-sequence":[1],"models,":[2],"particularly":[3],"the":[4,7,10,68,94,97],"Transformer,":[5],"are":[6,19],"state":[8],"of":[9,70,93],"art":[11],"in":[12,64],"machine":[13],"translation.":[14],"Yet":[15],"these":[16,28],"neural":[17],"networks":[18],"very":[20,73],"sensitive":[21],"to":[22,61,87],"architecture":[23,49],"and":[24],"hyperparameter":[25],"settings.":[26],"Optimizing":[27],"settings":[29],"by":[30,85],"grid":[31],"or":[32],"random":[33],"search":[34,50],"is":[35],"computationally":[36],"expensive":[37],"because":[38],"it":[39],"requires":[40],"many":[41],"training":[42,54],"runs.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,77],"incorporate":[48],"into":[51],"a":[52,65],"single":[53],"run":[55],"through":[56],"autosizing,":[57],"which":[58],"uses":[59],"regularization":[60],"delete":[62],"neurons":[63],"network":[66],"over":[67],"course":[69],"training.":[71],"On":[72],"low-resource":[74],"language":[75],"pairs,":[76],"show":[78],"that":[79],"auto-sizing":[80],"can":[81],"improve":[82],"BLEU":[83],"scores":[84],"up":[86],"3.9":[88],"points":[89],"while":[90],"removing":[91],"one-third":[92],"parameters":[95],"from":[96],"model.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}