{"id":"https://openalex.org/W2986267869","doi":"https://doi.org/10.26615/978-954-452-056-4_028","title":"Dependency-Based Self-Attention for Transformer NMT","display_name":"Dependency-Based Self-Attention for Transformer NMT","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2986267869","doi":"https://doi.org/10.26615/978-954-452-056-4_028","mag":"2986267869"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_028","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_028","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_028","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_028","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044944765","display_name":"Hiroyuki Deguchi","orcid":"https://orcid.org/0000-0003-2127-6607"},"institutions":[{"id":"https://openalex.org/I43545212","display_name":"Ehime University","ror":"https://ror.org/017hkng22","country_code":"JP","type":"education","lineage":["https://openalex.org/I43545212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyuki Deguchi","raw_affiliation_strings":["Ehime University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ehime University","institution_ids":["https://openalex.org/I43545212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102926384","display_name":"Akihiro Tamura","orcid":"https://orcid.org/0000-0003-4622-7713"},"institutions":[{"id":"https://openalex.org/I43545212","display_name":"Ehime University","ror":"https://ror.org/017hkng22","country_code":"JP","type":"education","lineage":["https://openalex.org/I43545212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Tamura","raw_affiliation_strings":["Ehime University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ehime University","institution_ids":["https://openalex.org/I43545212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019511958","display_name":"Takashi Ninomiya","orcid":"https://orcid.org/0000-0002-9703-2556"},"institutions":[{"id":"https://openalex.org/I43545212","display_name":"Ehime University","ror":"https://ror.org/017hkng22","country_code":"JP","type":"education","lineage":["https://openalex.org/I43545212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Ninomiya","raw_affiliation_strings":["Ehime University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ehime University","institution_ids":["https://openalex.org/I43545212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43545212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.968500018119812,"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":0.788280725479126},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.711095929145813},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6324754953384399},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6154447793960571},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6002473831176758},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5948245525360107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5337629914283752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5056314468383789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4702780544757843},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4345118999481201},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10089263319969177},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10079854726791382},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09392377734184265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788280725479126},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.711095929145813},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6324754953384399},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6154447793960571},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6002473831176758},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5948245525360107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5337629914283752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5056314468383789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4702780544757843},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4345118999481201},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10089263319969177},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10079854726791382},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09392377734184265},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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:10.26615/978-954-452-056-4_028","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_028","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_028","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_028","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_028","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_028","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2986267869.pdf","grobid_xml":"https://content.openalex.org/works/W2986267869.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2018116550","https://openalex.org/W2101105183","https://openalex.org/W2127863960","https://openalex.org/W2130942839","https://openalex.org/W2183341477","https://openalex.org/W2525778437","https://openalex.org/W2552110825","https://openalex.org/W2576482813","https://openalex.org/W2594047108","https://openalex.org/W2613904329","https://openalex.org/W2758137671","https://openalex.org/W2884083742","https://openalex.org/W2962784628","https://openalex.org/W2962788148","https://openalex.org/W2963073938","https://openalex.org/W2963403868","https://openalex.org/W2963571341","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W2949968076","https://openalex.org/W4384264648","https://openalex.org/W2935811960","https://openalex.org/W4389471172","https://openalex.org/W2969407538","https://openalex.org/W2917049097"],"abstract_inverted_index":{"In":[0],"this":[1,64],"paper,":[2],"we":[3],"propose":[4],"a":[5,101],"new":[6],"Transformer":[7,58,69],"neural":[8],"machine":[9],"translation":[10,120],"(NMT)":[11],"model":[12,99,110],"that":[13,97],"incorporates":[14],"dependency":[15,45],"relations":[16],"into":[17],"self-attention":[18,50],"on":[19,43,75,111],"both":[20],"source":[21],"and":[22],"target":[23],"sides,":[24],"dependency-based":[25,28,80,84],"selfattention.":[26],"The":[27],"selfattention":[29,85],"is":[30],"trained":[31],"to":[32,34,68],"attend":[33],"the":[35,44,78,108,112],"modifiee":[36],"for":[37,57,60],"each":[38],"token":[39],"under":[40],"constraints":[41],"based":[42],"relations,":[46],"inspired":[47],"by":[48,71,91],"linguistically-informed":[49],"(LISA).":[51],"While":[52],"LISA":[53,67],"was":[54],"originally":[55],"designed":[56],"encoder":[59],"semantic":[61],"role":[62],"labeling,":[63],"paper":[65],"extends":[66],"NMT":[70],"masking":[72],"future":[73],"information":[74],"words":[76],"in":[77,105],"decoderside":[79],"self-attention.":[81],"Additionally,":[82],"our":[83,98],"operates":[86],"at":[87],"subword":[88],"units":[89],"created":[90],"byte":[92],"pair":[93],"encoding.":[94],"Experiments":[95],"demonstrate":[96],"achieved":[100],"1.0":[102],"point":[103],"gain":[104],"BLEU":[106],"over":[107],"baseline":[109],"WAT'18":[113],"Asian":[114],"Scientific":[115],"Paper":[116],"Excerpt":[117],"Corpus":[118],"Japanese-to-English":[119],"task.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-11-22T00:00:00"}