{"id":"https://openalex.org/W2514713644","doi":"https://doi.org/10.18653/v1/e17-2025","title":"Using the Output Embedding to Improve Language Models","display_name":"Using the Output Embedding to Improve Language Models","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2514713644","doi":"https://doi.org/10.18653/v1/e17-2025","mag":"2514713644"},"language":"en","primary_location":{"id":"doi:10.18653/v1/e17-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2025","pdf_url":"https://www.aclweb.org/anthology/E17-2025.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 2, Short Papers","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/E17-2025.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035538068","display_name":"Ofir Press","orcid":null},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]},{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Ofir Press","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel","University of Washington, Seattle, United States"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"University of Washington, Seattle, United States","institution_ids":["https://openalex.org/I58610484","https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel","Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035538068"],"corresponding_institution_ids":["https://openalex.org/I16391192","https://openalex.org/I201448701","https://openalex.org/I58610484"],"apc_list":null,"apc_paid":null,"fwci":14.7295,"has_fulltext":true,"cited_by_count":91,"citation_normalized_percentile":{"value":0.99097527,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/embedding","display_name":"Embedding","score":0.9137629270553589},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7754117250442505},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.700255811214447},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.637617826461792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6240537166595459},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5184123516082764},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5165354609489441},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48118478059768677},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4463568329811096},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4251590669155121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3449309468269348}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.9137629270553589},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7754117250442505},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.700255811214447},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.637617826461792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6240537166595459},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5184123516082764},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5165354609489441},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48118478059768677},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4463568329811096},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4251590669155121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3449309468269348},{"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/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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":4,"locations":[{"id":"doi:10.18653/v1/e17-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2025","pdf_url":"https://www.aclweb.org/anthology/E17-2025.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 2, Short Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.05859","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.05859","pdf_url":"https://arxiv.org/pdf/1608.05859","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:2514713644","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1608.05859.pdf","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.1608.05859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.05859","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/e17-2025","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2025","pdf_url":"https://www.aclweb.org/anthology/E17-2025.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 2, Short Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2514713644.pdf","grobid_xml":"https://content.openalex.org/works/W2514713644.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W46679369","https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W1753482797","https://openalex.org/W1810943226","https://openalex.org/W1821462560","https://openalex.org/W1854884267","https://openalex.org/W1889624880","https://openalex.org/W1905522558","https://openalex.org/W1943583106","https://openalex.org/W2064675550","https://openalex.org/W2112184938","https://openalex.org/W2113459411","https://openalex.org/W2118776487","https://openalex.org/W2129250947","https://openalex.org/W2131462252","https://openalex.org/W2131571251","https://openalex.org/W2132339004","https://openalex.org/W2142625445","https://openalex.org/W2171928131","https://openalex.org/W2176085882","https://openalex.org/W2183112036","https://openalex.org/W2212703438","https://openalex.org/W2251012068","https://openalex.org/W2260194779","https://openalex.org/W2292877769","https://openalex.org/W2402268235","https://openalex.org/W2417736714","https://openalex.org/W2418388682","https://openalex.org/W2473934411","https://openalex.org/W2533523411","https://openalex.org/W2549416390","https://openalex.org/W2553303224","https://openalex.org/W2949888546","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2950635152","https://openalex.org/W2950797609","https://openalex.org/W2962784628","https://openalex.org/W2964059111","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W1522301498","https://openalex.org/W2964308564","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2963403868","https://openalex.org/W2962784628","https://openalex.org/W2549416390","https://openalex.org/W2525332836","https://openalex.org/W1591801644","https://openalex.org/W2963347649","https://openalex.org/W2525778437","https://openalex.org/W2963266340","https://openalex.org/W2101105183","https://openalex.org/W2963341956","https://openalex.org/W179875071","https://openalex.org/W1632114991","https://openalex.org/W2949888546","https://openalex.org/W1902237438","https://openalex.org/W2743945814","https://openalex.org/W2250539671"],"abstract_inverted_index":{"We":[0,11,35,66],"study":[1],"the":[2,28,37,44,54,59,63,74,108],"topmost":[3],"weight":[4,104],"matrix":[5,15],"of":[6,72,95,110,118],"neural":[7,96,111],"network":[8,97],"language":[9,23,98],"models.":[10,99],"show":[12,42,91,102],"that":[13,43,103],"this":[14,32],"constitutes":[16],"a":[17,49,69,81,93],"valid":[18],"word":[19],"embedding.":[20,34,76],"When":[21],"training":[22],"models,":[24],"we":[25,87,101],"recommend":[26],"tying":[27,105],"input":[29,60],"embedding":[30,46,56,61],"and":[31,41],"output":[33,55,75],"analyze":[36],"resulting":[38],"update":[39],"rules":[40],"tied":[45],"evolves":[47],"in":[48,62,84],"more":[50],"similar":[51],"way":[52],"to":[53,58,80,90,114],"than":[57,116],"untied":[64],"model.":[65],"also":[67],"offer":[68],"new":[70],"method":[71],"regularizing":[73],"Our":[77],"methods":[78],"lead":[79],"significant":[82],"reduction":[83],"perplexity,":[85],"as":[86],"are":[88],"able":[89],"on":[92],"variety":[94],"Finally,":[100],"can":[106],"reduce":[107],"size":[109,121],"translation":[112],"models":[113],"less":[115],"half":[117],"their":[119,124],"original":[120],"without":[122],"harming":[123],"performance.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}