{"id":"https://openalex.org/W2956141336","doi":"https://doi.org/10.18653/v1/w19-5211","title":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","display_name":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2956141336","doi":"https://doi.org/10.18653/v1/w19-5211","mag":"2956141336"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5211","pdf_url":"https://www.aclweb.org/anthology/W19-5211.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5211.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060107290","display_name":"Denis Emelin","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":"Denis Emelin","raw_affiliation_strings":["University of Edinburgh, Scotland","University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"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":["University of Amsterdam, Netherlands","University of Edinburgh, Scotland","University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"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":["University of Edinburgh, Scotland","University of Zurich, Switzerland","University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06252101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"115"},"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":0.9912999868392944,"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":0.7922424077987671},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7641136646270752},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6960077285766602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6020584106445312},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5914502143859863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5895043015480042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5813801288604736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4367482662200928},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41725990176200867},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41511625051498413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34461212158203125},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06501379609107971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922424077987671},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7641136646270752},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6960077285766602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6020584106445312},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5914502143859863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5895043015480042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5813801288604736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4367482662200928},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41725990176200867},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41511625051498413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34461212158203125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06501379609107971},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.18653/v1/w19-5211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5211","pdf_url":"https://www.aclweb.org/anthology/W19-5211.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/9f101a04-e6f5-4ba7-95e7-9bda9e4ea37f","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/widening-the-representation-bottleneck-in-neural-machine-translation-with-lexical-shortcuts(9f101a04-e6f5-4ba7-95e7-9bda9e4ea37f).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:172624","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":"Emelin, Denis; Titov, Ivan; Sennrich, Rico (2019). Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts. In: ACL 2019 FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT19), Florence, Italy, 1 August 2019 - 2 August 2019. ACL, 102-115.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1906.12284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.12284","pdf_url":"https://arxiv.org/pdf/1906.12284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"mag:2956141336","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.12284.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:dare.uva.nl:publications/9f101a04-e6f5-4ba7-95e7-9bda9e4ea37f","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/9f101a04-e6f5-4ba7-95e7-9bda9e4ea37f","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/40d7489e-597a-438d-8ef8-e079b07cab0a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/40d7489e-597a-438d-8ef8-e079b07cab0a","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":"Emelin, D, Titov, I & Sennrich, R 2019, Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts. in Proceedings of the Fourth Conference on Machine Translation (WMT), Volume 1 : Research Papers. vol. 1, Florence, Italy, pp. 102\u2013115, ACL 2019 Fourth Conference on Machine Translation, Florence, Italy, 1/08/19. https://doi.org/10.18653/v1/W19-5211","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/40d7489e-597a-438d-8ef8-e079b07cab0a","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/40d7489e-597a-438d-8ef8-e079b07cab0a","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":"Emelin, D, Titov, I & Sennrich, R 2019, Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts. in Proceedings of the Fourth Conference on Machine Translation (WMT), Volume 1 : Research Papers. vol. 1, Florence, Italy, pp. 102\u2013115, ACL 2019 Fourth Conference on Machine Translation, Florence, Italy, 1/08/19. https://doi.org/10.18653/v1/W19-5211","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1906.12284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.12284","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},{"id":"doi:10.5167/uzh-172624","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-172624","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/w19-5211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5211","pdf_url":"https://www.aclweb.org/anthology/W19-5211.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1309768829","display_name":null,"funder_award_id":"EP/N510129/1.","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"Horizon2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6458387989","display_name":"Global Under-Resourced MEedia Translation","funder_award_id":"825299","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2956141336.pdf","grobid_xml":"https://content.openalex.org/works/W2956141336.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522263329","https://openalex.org/W1522301498","https://openalex.org/W1951216520","https://openalex.org/W2095705004","https://openalex.org/W2194775991","https://openalex.org/W2514713644","https://openalex.org/W2560864221","https://openalex.org/W2563574619","https://openalex.org/W2605717780","https://openalex.org/W2759173152","https://openalex.org/W2764124976","https://openalex.org/W2787802257","https://openalex.org/W2798280127","https://openalex.org/W2798362442","https://openalex.org/W2798687821","https://openalex.org/W2892116303","https://openalex.org/W2896060389","https://openalex.org/W2903193068","https://openalex.org/W2949242443","https://openalex.org/W2949454572","https://openalex.org/W2950399211","https://openalex.org/W2950635152","https://openalex.org/W2962777840","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963418779","https://openalex.org/W2963446712","https://openalex.org/W2963970792"],"related_works":["https://openalex.org/W3030299276","https://openalex.org/W2531738943","https://openalex.org/W2147925066","https://openalex.org/W2103222490","https://openalex.org/W3100650951","https://openalex.org/W2977788613","https://openalex.org/W2404517620","https://openalex.org/W2564413943","https://openalex.org/W2034639451","https://openalex.org/W3168616017","https://openalex.org/W2741239863","https://openalex.org/W1508023352","https://openalex.org/W2897303468","https://openalex.org/W2766742239","https://openalex.org/W2791412059","https://openalex.org/W2943085977","https://openalex.org/W2977057303","https://openalex.org/W2949832505","https://openalex.org/W2952208079","https://openalex.org/W2953483091"],"abstract_inverted_index":{"The":[0],"transformer":[1,122,159],"is":[2],"a":[3,34,120],"state-of-the-art":[4],"neural":[5],"translation":[6,126,130],"model":[7,93,172],"that":[8,42,112],"uses":[9],"attention":[10],"to":[11,45,65,94,153],"iteratively":[12],"refine":[13],"lexical":[14,49,97,141,155],"representations":[15],"with":[16],"information":[17,63,142],"drawn":[18],"from":[19],"the":[20,28,43,55,66,78,86,92,113,138,145,158,166],"surrounding":[21],"context.":[22],"Lexical":[23],"features":[24,50],"are":[25],"fed":[26],"into":[27,157],"first":[29],"layer":[30,53,80,84],"and":[31,47,60,81,88,136,161],"propagated":[32],"through":[33],"deep":[35],"network":[36],"of":[37,140,168],"hidden":[38,146],"layers.":[39,147],"We":[40,110,148],"argue":[41],"need":[44],"represent":[46],"propagate":[48],"in":[51,128],"each":[52,82],"limits":[54],"model's":[56],"capacity":[57],"for":[58],"learning":[59],"representing":[61],"other":[62],"relevant":[64,96],"task.":[67],"To":[68],"alleviate":[69],"this":[70],"bottleneck,":[71],"we":[72],"introduce":[73],"gated":[74],"shortcut":[75],"connections":[76,156],"between":[77],"embedding":[79],"subsequent":[83],"within":[85,107],"encoder":[87],"decoder.":[89],"This":[90],"enables":[91],"access":[95],"content":[98],"dynamically,":[99],"without":[100],"expending":[101],"limited":[102],"resources":[103],"on":[104,123,134,171],"storing":[105],"it":[106],"intermediate":[108],"states.":[109],"show":[111],"proposed":[114,169],"modification":[115],"yields":[116],"consistent":[117],"improvements":[118],"over":[119],"baseline":[121],"standard":[124],"WMT":[125],"tasks":[127],"5":[129],"directions":[131],"(0.9":[132],"BLEU":[133],"average)":[135],"reduces":[137],"amount":[139],"passed":[143],"along":[144],"furthermore":[149],"evaluate":[150],"different":[151],"ways":[152],"integrate":[154],"architecture":[160],"present":[162],"ablation":[163],"experiments":[164],"exploring":[165],"effect":[167],"shortcuts":[170],"behavior.":[173],"1":[174]},"counts_by_year":[],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2022-07-28T00:00:00"}