{"id":"https://openalex.org/W3119262703","doi":"https://doi.org/10.18653/v1/2020.wmt-1.17","title":"Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task","display_name":"Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3119262703","doi":"https://doi.org/10.18653/v1/2020.wmt-1.17","mag":"3119262703"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.17","pdf_url":"https://aclanthology.org/2020.wmt-1.17.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.17.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027569258","display_name":"Ulrich Germann","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ulrich Germann","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023392498","display_name":"Roman Grundkiewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roman Grundkiewicz","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083887502","display_name":"Martin Popel","orcid":"https://orcid.org/0000-0002-3628-8419"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Popel","raw_affiliation_strings":["Charles University, Prague, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001125224","display_name":"Radina Dobreva","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Radina Dobreva","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018769709","display_name":"Nikolay Bogoychev","orcid":"https://orcid.org/0000-0003-4373-5261"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolay Bogoychev","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"196"},"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":0.9957000017166138,"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":0.7691401839256287},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7176625728607178},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6362868547439575},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5705549716949463},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5467081069946289},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5093446969985962},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.45923149585723877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4266453683376312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41127872467041016},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10101550817489624},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09929749369621277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691401839256287},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7176625728607178},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6362868547439575},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5705549716949463},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5467081069946289},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5093446969985962},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.45923149585723877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4266453683376312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41127872467041016},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10101550817489624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09929749369621277},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.17","pdf_url":"https://aclanthology.org/2020.wmt-1.17.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d73867d0-a0e4-41db-9ca8-6325dfe5036e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d73867d0-a0e4-41db-9ca8-6325dfe5036e","pdf_url":"https://www.aclweb.org/anthology/2020.wmt-1.17","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Germann, U, Grundkiewicz, R, Popel, M, Dobreva, R, Bogoychev, N & Heafield, K 2020, Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task. in Proceedings of the Fifth Conference on Machine Translation. Online, pp. 191-196. < https://www.aclweb.org/anthology/2020.wmt-1.17 >","raw_type":"contributionToPeriodical"},{"id":"mag:3119262703","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.17.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.17","pdf_url":"https://aclanthology.org/2020.wmt-1.17.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2465893628","display_name":"Peta-5: A National Facility for Petascale Data Intensive Computation and Analytics","funder_award_id":"EP/P020259/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5258663329","display_name":null,"funder_award_id":"EP/P020259/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6476763384","display_name":"European Language Grid","funder_award_id":"825627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6972900625","display_name":"Browser-based Multilingual Translation","funder_award_id":"825303","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320312927","display_name":"Dell EMC","ror":"https://ror.org/05rejmm18"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119262703.pdf","grobid_xml":"https://content.openalex.org/works/W3119262703.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2148708890","https://openalex.org/W2153653739","https://openalex.org/W2805493160","https://openalex.org/W2902767466","https://openalex.org/W2962834107","https://openalex.org/W2962906592","https://openalex.org/W2963216553","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2963418779","https://openalex.org/W2963532001","https://openalex.org/W2963626623","https://openalex.org/W2964299589","https://openalex.org/W2983981554","https://openalex.org/W2987188351","https://openalex.org/W3039986555","https://openalex.org/W3045818398","https://openalex.org/W3045883122","https://openalex.org/W3082760180","https://openalex.org/W3120000557","https://openalex.org/W3211259717"],"related_works":["https://openalex.org/W3120964679","https://openalex.org/W2970259631","https://openalex.org/W2902081112","https://openalex.org/W2964240726","https://openalex.org/W2903193068","https://openalex.org/W3214258555","https://openalex.org/W3119961061","https://openalex.org/W3097240187","https://openalex.org/W2418388682","https://openalex.org/W2970659112","https://openalex.org/W3095125651","https://openalex.org/W3092058109","https://openalex.org/W2970544750","https://openalex.org/W2971074957","https://openalex.org/W2740433069","https://openalex.org/W2889545026","https://openalex.org/W2970705013","https://openalex.org/W3118955479","https://openalex.org/W2903490366","https://openalex.org/W2977881703"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,6,15,19,52],"joint":[3],"submission":[4],"of":[5,8,63],"University":[7],"Edinburgh":[9],"and":[10,28,49],"Charles":[11],"University,":[12],"Prague,":[13],"to":[14,41],"Czech/English":[16],"track":[17],"in":[18],"WMT":[20,53],"2020":[21,54],"Shared":[22],"Task":[23],"on":[24,72,82],"News":[25],"Translation.Our":[26],"fast":[27],"compact":[29],"student":[30],"models":[31],"distill":[32],"knowledge":[33],"from":[34],"a":[35,43,73,86],"larger,":[36],"slower":[37],"teacher.They":[38],"are":[39],"designed":[40],"offer":[42],"good":[44],"trade-off":[45],"between":[46],"translation":[47,61,80],"quality":[48],"inference":[50],"efficiency.On":[51],"Czech":[55],"English":[56],"test":[57],"sets,":[58],"they":[59],"achieve":[60],"speeds":[62],"over":[64],"700":[65],"whitespacedelimited":[66],"source":[67],"words":[68],"per":[69],"second":[70],"1":[71],"single":[74],"CPU":[75],"thread,":[76],"thus":[77],"making":[78],"neural":[79],"feasible":[81],"consumer":[83],"hardware":[84],"without":[85],"GPU.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2021-01-18T00:00:00"}