{"id":"https://openalex.org/W2890249489","doi":"https://doi.org/10.18653/v1/d18-1319","title":"Bayesian Compression for Natural Language Processing","display_name":"Bayesian Compression for Natural Language Processing","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890249489","doi":"https://doi.org/10.18653/v1/d18-1319","mag":"2890249489"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1319","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1319","pdf_url":"https://www.aclweb.org/anthology/D18-1319.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 2018 Conference on Empirical Methods in Natural Language Processing","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/D18-1319.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046785127","display_name":"Nadezhda Chirkova","orcid":"https://orcid.org/0000-0001-8188-3391"},"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/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB","RU"],"is_corresponding":false,"raw_author_name":"Nadezhda Chirkova","raw_affiliation_strings":["Samsung-HSE Laboratory, National Research University Higher School of Economics","National Research University Higher School of Economics, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung-HSE Laboratory, National Research University Higher School of Economics","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210117523"]},{"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/A5109729955","display_name":"Ekaterina Lobacheva","orcid":null},"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/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB","RU"],"is_corresponding":false,"raw_author_name":"Ekaterina Lobacheva","raw_affiliation_strings":["Samsung-HSE Laboratory, National Research University Higher School of Economics","National Research University Higher School of Economics, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung-HSE Laboratory, National Research University Higher School of Economics","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210117523"]},{"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/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]},{"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":["GB","RU"],"is_corresponding":false,"raw_author_name":"Dmitry Vetrov","raw_affiliation_strings":["Samsung AI Center Moscow, Russia","Samsung-HSE Laboratory, National Research University Higher School of Economics","National Research University Higher School of Economics, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center Moscow, Russia","institution_ids":["https://openalex.org/I4210141363"]},{"raw_affiliation_string":"Samsung-HSE Laboratory, National Research University Higher School of Economics","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210117523"]},{"raw_affiliation_string":"National Research University Higher School of Economics, Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6758,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77828404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2910","last_page":"2915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8194568157196045},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7459107637405396},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5965288877487183},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5766544342041016},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5762162208557129},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5691722631454468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5074257254600525},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4707534909248352},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4706282615661621},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46865931153297424},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4384000897407532},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42311742901802063},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.412864625453949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4015216529369354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3969862461090088},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3588520884513855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.347485214471817},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13333112001419067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194568157196045},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7459107637405396},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5965288877487183},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5766544342041016},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5762162208557129},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5691722631454468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074257254600525},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4707534909248352},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4706282615661621},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46865931153297424},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4384000897407532},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42311742901802063},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.412864625453949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4015216529369354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3969862461090088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3588520884513855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.347485214471817},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13333112001419067},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d18-1319","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1319","pdf_url":"https://www.aclweb.org/anthology/D18-1319.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.10927","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.10927","pdf_url":"https://arxiv.org/pdf/1810.10927","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":"","raw_type":"text"},{"id":"mag:2890249489","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.10927","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.1810.10927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.10927","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/d18-1319","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1319","pdf_url":"https://www.aclweb.org/anthology/D18-1319.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G843664032","display_name":null,"funder_award_id":"17-71-20072","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890249489.pdf","grobid_xml":"https://content.openalex.org/works/W2890249489.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1632114991","https://openalex.org/W1800356822","https://openalex.org/W2113459411","https://openalex.org/W2171928131","https://openalex.org/W2250539671","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2606554264","https://openalex.org/W2608554408","https://openalex.org/W2617991662","https://openalex.org/W2619890685","https://openalex.org/W2619959423","https://openalex.org/W2754526845","https://openalex.org/W2949218037","https://openalex.org/W2950133940","https://openalex.org/W2950894517","https://openalex.org/W2951595529","https://openalex.org/W2963266340","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2964293190","https://openalex.org/W2546915671","https://openalex.org/W2769137120","https://openalex.org/W196214544","https://openalex.org/W2970421595","https://openalex.org/W2999730493","https://openalex.org/W2949059244","https://openalex.org/W3089122997","https://openalex.org/W2867192824","https://openalex.org/W2971306187","https://openalex.org/W2914294010","https://openalex.org/W2533339295","https://openalex.org/W2808168001","https://openalex.org/W2733236492","https://openalex.org/W2747579829","https://openalex.org/W2993091699","https://openalex.org/W2796353546","https://openalex.org/W2437096199","https://openalex.org/W2905016804","https://openalex.org/W2791521493"],"abstract_inverted_index":{"In":[0],"natural":[1],"language":[2],"processing,":[3],"a":[4,20,47],"lot":[5],"of":[6,23,27,61,91],"the":[7,34,42,56,70,82,89,92],"tasks":[8],"are":[9,30],"successfully":[10],"solved":[11],"with":[12],"recurrent":[13],"neural":[14],"networks,":[15],"but":[16],"such":[17],"models":[18],"have":[19],"huge":[21],"number":[22],"parameters.":[24],"The":[25],"majority":[26],"these":[28],"parameters":[29],"often":[31],"concentrated":[32],"in":[33],"embedding":[35],"layer,":[36],"which":[37,53],"size":[38],"grows":[39],"proportionally":[40],"to":[41,75],"vocabulary":[43,73],"length.":[44],"We":[45,67,86],"propose":[46],"Bayesian":[48],"sparsification":[49,74],"technique":[50],"for":[51,72],"RNNs":[52],"allows":[54],"compressing":[55],"RNN":[57,83],"dozens":[58],"or":[59],"hundreds":[60],"times":[62],"without":[63],"time-consuming":[64],"hyperparameters":[65],"tuning.":[66],"also":[68],"generalize":[69],"model":[71],"filter":[76],"out":[77],"unnecessary":[78],"words":[79,94],"and":[80],"compress":[81],"even":[84],"further.":[85],"show":[87],"that":[88],"choice":[90],"kept":[93],"is":[95],"interpretable.":[96]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}