{"id":"https://openalex.org/W2970290486","doi":"https://doi.org/10.18653/v1/d19-1083","title":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","display_name":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970290486","doi":"https://doi.org/10.18653/v1/d19-1083","mag":"2970290486"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1083","pdf_url":"https://www.aclweb.org/anthology/D19-1083.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-1083.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100363719","display_name":"Biao Zhang","orcid":"https://orcid.org/0000-0002-4865-7090"},"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":"Biao Zhang","raw_affiliation_strings":["School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086717154","display_name":"Ivan Titov","orcid":"https://orcid.org/0000-0002-2583-1893"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"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","NL"],"is_corresponding":false,"raw_author_name":"Ivan Titov","raw_affiliation_strings":["ILLC, University of Amsterdam","School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005771535","display_name":"Rico Sennrich","orcid":"https://orcid.org/0000-0002-1438-4741"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"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":["CH","GB"],"is_corresponding":false,"raw_author_name":"Rico Sennrich","raw_affiliation_strings":["Institute of Computational Linguistics, University of Zurich","School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","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":7.7561,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.97956303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"898","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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":0.9965999722480774,"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/initialization","display_name":"Initialization","score":0.7729650735855103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923530101776123},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5839574933052063},{"id":"https://openalex.org/keywords/zh\u00e0ng","display_name":"Zh\u00e0ng","score":0.5269977450370789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46391358971595764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4598124921321869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33897703886032104},{"id":"https://openalex.org/keywords/china","display_name":"China","score":0.17028272151947021},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16594842076301575},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1628229320049286},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15957340598106384},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.11528274416923523}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7729650735855103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923530101776123},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5839574933052063},{"id":"https://openalex.org/C2777045944","wikidata":"https://www.wikidata.org/wiki/Q12170198","display_name":"Zh\u00e0ng","level":3,"score":0.5269977450370789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46391358971595764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4598124921321869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33897703886032104},{"id":"https://openalex.org/C191935318","wikidata":"https://www.wikidata.org/wiki/Q148","display_name":"China","level":2,"score":0.17028272151947021},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16594842076301575},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1628229320049286},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15957340598106384},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.11528274416923523},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.18653/v1/d19-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1083","pdf_url":"https://www.aclweb.org/anthology/D19-1083.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/improving-deep-transformer-with-depthscaled-initialization-and-merged-attention(2b6ad5cf-80b9-403d-8013-8da5f3968dc6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.zora.uzh.ch:176330","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Zhang, Biao; Titov, Ivan; Sennrich, Rico (2019). Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, 3 November 2019 - 7 November 2019. Association for Computational Linguistics, 897-908.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:publications/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","is_oa":false,"landing_page_url":"http://hdl.handle.net/11245.1/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:dare.uva.nl:publications/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/dab53e26-0f96-4b57-9cd6-6f689e88b037","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/dab53e26-0f96-4b57-9cd6-6f689e88b037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/dab53e26-0f96-4b57-9cd6-6f689e88b037","is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/D19-1083","pdf_url":null,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/2b6ad5cf-80b9-403d-8013-8da5f3968dc6","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/improving-deep-transformer-with-depthscaled-initialization-and-merged-attention(2b6ad5cf-80b9-403d-8013-8da5f3968dc6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing: EMNLP-IJCNLP 2019 : proceedings of the conference : November 3-7, 2019, Hong Kong, China, 898 - 909","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.5167/uzh-176330","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-176330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1083","pdf_url":"https://www.aclweb.org/anthology/D19-1083.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1535130713","display_name":null,"funder_award_id":"H2020-ICT","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6031099476","display_name":"European Live Translator","funder_award_id":"825460","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6661763476","display_name":null,"funder_award_id":"EP/P020259/1","funder_id":"https://openalex.org/F4320320273","funder_display_name":"University of Cambridge"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970290486.pdf","grobid_xml":"https://content.openalex.org/works/W2970290486.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1603870118","https://openalex.org/W1686810756","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2257408573","https://openalex.org/W2525778437","https://openalex.org/W2594990650","https://openalex.org/W2613904329","https://openalex.org/W2767206889","https://openalex.org/W2805493160","https://openalex.org/W2888520903","https://openalex.org/W2897983179","https://openalex.org/W2903193068","https://openalex.org/W2908336025","https://openalex.org/W2912521296","https://openalex.org/W2940744433","https://openalex.org/W2952809536","https://openalex.org/W2962784628","https://openalex.org/W2962835968","https://openalex.org/W2963091079","https://openalex.org/W2963248296","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963542740","https://openalex.org/W2963599677","https://openalex.org/W2963713328","https://openalex.org/W2963807318","https://openalex.org/W2963946353","https://openalex.org/W2963991316","https://openalex.org/W2964045208","https://openalex.org/W2964213727","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2970690146","https://openalex.org/W2972451902","https://openalex.org/W3041866211","https://openalex.org/W4289302788","https://openalex.org/W4297687616","https://openalex.org/W4297747548","https://openalex.org/W4300852664","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W4394650345","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2364559953","https://openalex.org/W2375840727","https://openalex.org/W2389678104","https://openalex.org/W2375137083","https://openalex.org/W2380507695","https://openalex.org/W2367687999","https://openalex.org/W3204184292","https://openalex.org/W2387562377","https://openalex.org/W2384722335","https://openalex.org/W2376544228"],"abstract_inverted_index":{"Biao":[0],"Zhang,":[1],"Ivan":[2],"Titov,":[3],"Rico":[4],"Sennrich.":[5],"Proceedings":[6],"of":[7],"the":[8,19],"2019":[9],"Conference":[10,23],"on":[11,24],"Empirical":[12],"Methods":[13],"in":[14],"Natural":[15,25],"Language":[16,26],"Processing":[17,27],"and":[18],"9th":[20],"International":[21],"Joint":[22],"(EMNLP-IJCNLP).":[28],"2019.":[29]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}