{"id":"https://openalex.org/W2971090208","doi":"https://doi.org/10.18653/v1/w19-4306","title":"Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks","display_name":"Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2971090208","doi":"https://doi.org/10.18653/v1/w19-4306","mag":"2971090208"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4306","pdf_url":"https://www.aclweb.org/anthology/W19-4306.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4306.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082003088","display_name":"Maxim Kodryan","orcid":"https://orcid.org/0000-0002-6554-5672"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]},{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Maxim Kodryan","raw_affiliation_strings":["National Research University Higher School of Economics Moscow, Russia","Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","Moscow State University Moscow, Russia","Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Moscow State University Moscow, Russia","institution_ids":["https://openalex.org/I19880235"]},{"raw_affiliation_string":"Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019759699","display_name":"Artem M. Grachev","orcid":"https://orcid.org/0000-0002-0268-6363"},"institutions":[{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]},{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Artem Grachev","raw_affiliation_strings":["Moscow State University Moscow, Russia","Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","National Research University Higher School of Economics Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Moscow State University Moscow, Russia","institution_ids":["https://openalex.org/I19880235"]},{"raw_affiliation_string":"Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002385420","display_name":"Dmitry I. Ignatov","orcid":"https://orcid.org/0000-0002-6584-8534"},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]},{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Ignatov","raw_affiliation_strings":["Moscow State University Moscow, Russia","Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","National Research University Higher School of Economics Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Moscow State University Moscow, Russia","institution_ids":["https://openalex.org/I19880235"]},{"raw_affiliation_string":"Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101595563","display_name":"Dmitry Vetrov","orcid":"https://orcid.org/0000-0001-6863-9028"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]},{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Vetrov","raw_affiliation_strings":["Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","National Research University Higher School of Economics Moscow, Russia","Moscow State University Moscow, Russia","Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Samsung AI Center, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]},{"raw_affiliation_string":"National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"Moscow State University Moscow, Russia","institution_ids":["https://openalex.org/I19880235"]},{"raw_affiliation_string":"Samsung R&D Institute, National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210141363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019759699"],"corresponding_institution_ids":["https://openalex.org/I118501908","https://openalex.org/I19880235","https://openalex.org/I4210141363"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58185371,"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":"40","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9966999888420105,"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":0.8141154646873474},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6789681911468506},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.6461085677146912},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.637631893157959},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5742346048355103},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.572101891040802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5486364364624023},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5183637738227844},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4703916311264038},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45919904112815857},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42786872386932373},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4166529178619385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37501463294029236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141154646873474},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6789681911468506},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.6461085677146912},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.637631893157959},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5742346048355103},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.572101891040802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5486364364624023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5183637738227844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4703916311264038},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45919904112815857},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42786872386932373},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4166529178619385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37501463294029236},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4306","pdf_url":"https://www.aclweb.org/anthology/W19-4306.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4306","pdf_url":"https://www.aclweb.org/anthology/W19-4306.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G4854617120","display_name":null,"funder_award_id":"5-100","funder_id":"https://openalex.org/F4320324261","funder_display_name":"National Research University Higher School of Economics"}],"funders":[{"id":"https://openalex.org/F4320324261","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2971090208.pdf","grobid_xml":"https://content.openalex.org/works/W2971090208.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494853941","https://openalex.org/W1558797106","https://openalex.org/W1591801644","https://openalex.org/W2064675550","https://openalex.org/W2150807068","https://openalex.org/W2175402905","https://openalex.org/W2269892441","https://openalex.org/W2549416390","https://openalex.org/W2582745083","https://openalex.org/W2608554408","https://openalex.org/W2619890685","https://openalex.org/W2619959423","https://openalex.org/W2784590060","https://openalex.org/W2803125181","https://openalex.org/W2898870584","https://openalex.org/W2914294010","https://openalex.org/W2950821630","https://openalex.org/W2951595529","https://openalex.org/W2952088488","https://openalex.org/W2962964385","https://openalex.org/W2963042606","https://openalex.org/W2963347649","https://openalex.org/W2963494889","https://openalex.org/W2963537482","https://openalex.org/W2963932686","https://openalex.org/W2963991999","https://openalex.org/W2964094335","https://openalex.org/W2964110616","https://openalex.org/W2964199361","https://openalex.org/W2964293190","https://openalex.org/W2964299589","https://openalex.org/W2998704965","https://openalex.org/W3105213343","https://openalex.org/W4242379934","https://openalex.org/W4285719527","https://openalex.org/W4297689207","https://openalex.org/W4298422451"],"related_works":["https://openalex.org/W2998037107","https://openalex.org/W1597439699","https://openalex.org/W1569871744","https://openalex.org/W2016024526","https://openalex.org/W2379437105","https://openalex.org/W3139928442","https://openalex.org/W1567336638","https://openalex.org/W954011496","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"Reduction":[0],"of":[1,4,8,23,52,91],"the":[2,9,55,92],"number":[3,51],"parameters":[5,53],"is":[6,60],"one":[7],"most":[10],"important":[11],"goals":[12],"in":[13,45,54,94],"Deep":[14],"Learning.":[15],"In":[16],"this":[17,39],"article":[18],"we":[19],"propose":[20],"an":[21],"adaptation":[22],"Doubly":[24],"Stochastic":[25],"Variational":[26],"Inference":[27],"for":[28,33],"Automatic":[29],"Relevance":[30],"Determination":[31],"(DSVI-ARD)":[32],"neural":[34],"networks":[35],"compression.":[36],"We":[37,63],"find":[38],"method":[40],"to":[41,77],"be":[42,69,101],"especially":[43],"useful":[44],"language":[46],"modeling":[47],"tasks,":[48],"where":[49],"large":[50],"input":[56],"and":[57,82,97],"output":[58],"layers":[59,99],"often":[61],"excessive.":[62],"also":[64],"show":[65],"that":[66,87],"DSVI-ARD":[67],"can":[68,100],"applied":[70],"together":[71],"with":[72,103],"encoder-decoder":[73],"weight":[74],"tying":[75],"allowing":[76],"achieve":[78],"even":[79],"better":[80],"sparsity":[81],"performance.":[83],"Our":[84],"experiments":[85],"demonstrate":[86],"more":[88],"than":[89],"90%":[90],"weights":[93],"both":[95],"encoder":[96],"decoder":[98],"removed":[102],"a":[104],"minimal":[105],"quality":[106],"loss.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}