{"id":"https://openalex.org/W2888010645","doi":"https://doi.org/10.18653/v1/d18-1331","title":"Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation","display_name":"Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888010645","doi":"https://doi.org/10.18653/v1/d18-1331","mag":"2888010645"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1331","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1331","pdf_url":"https://www.aclweb.org/anthology/D18-1331.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1331.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Lin","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":["School of Foreign Languages, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Foreign Languages, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049239373","display_name":"Xuancheng Ren","orcid":"https://orcid.org/0000-0002-6994-2114"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xuancheng Ren","raw_affiliation_strings":["School of Foreign Languages, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Foreign Languages, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081449019","display_name":"Muyu Li","orcid":"https://orcid.org/0000-0001-7708-4474"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Muyu Li","raw_affiliation_strings":["School of Foreign Languages, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Foreign Languages, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066310925","display_name":"Qi Su","orcid":"https://orcid.org/0000-0002-4769-2812"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Su","raw_affiliation_strings":["MOE Key Lab of Computational Linguistics, School of EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of Computational Linguistics, School of EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3654,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91294406,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2985","last_page":"2990"},"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":0.9997000098228455,"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":0.9890999794006348,"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/machine-translation","display_name":"Machine translation","score":0.8452502489089966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570463418960571},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5881392359733582},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5747866034507751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698699355125427},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5478489398956299},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5380212068557739},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5333898663520813},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49630028009414673},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4903428554534912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43237537145614624},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41870665550231934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38622549176216125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20949065685272217},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11087816953659058}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8452502489089966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570463418960571},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5881392359733582},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5747866034507751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698699355125427},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5478489398956299},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5380212068557739},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5333898663520813},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49630028009414673},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4903428554534912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43237537145614624},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41870665550231934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38622549176216125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20949065685272217},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11087816953659058},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1331","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1331","pdf_url":"https://www.aclweb.org/anthology/D18-1331.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"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1331","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1331","pdf_url":"https://www.aclweb.org/anthology/D18-1331.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G7215211584","display_name":null,"funder_award_id":"61673028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336656","display_name":"Thousand Young Talents Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888010645.pdf","grobid_xml":"https://content.openalex.org/works/W2888010645.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1753482797","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2534200568","https://openalex.org/W2659803504","https://openalex.org/W2787534827","https://openalex.org/W2806591392","https://openalex.org/W2905927205","https://openalex.org/W2952479981","https://openalex.org/W2953830716","https://openalex.org/W2962954913","https://openalex.org/W2963246629","https://openalex.org/W2963260202","https://openalex.org/W2963403868","https://openalex.org/W2963541420","https://openalex.org/W2963699608","https://openalex.org/W2963891264","https://openalex.org/W2963970666","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3204406378","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3022757400","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2221419418","https://openalex.org/W2883671469"],"abstract_inverted_index":{"Most":[0],"of":[1,47,53,75,82,86,133],"the":[2,11,21,25,30,38,45,48,80,93,104,108,111,121,126,131],"Neural":[3],"Machine":[4],"Translation":[5],"(NMT)":[6],"models":[7],"are":[8],"based":[9],"on":[10,92],"sequence-tosequence":[12],"(Seq2Seq)":[13],"model":[14,68,102,117],"with":[15,20,37,69],"an":[16,87],"encoderdecoder":[17],"framework":[18],"equipped":[19],"attention":[22,27,49,83,88],"mechanism.":[23],"However,":[24],"conventional":[26],"mechanism":[28,71],"treats":[29],"decoding":[31],"at":[32],"each":[33],"time":[34],"step":[35],"equally":[36],"same":[39],"matrix,":[40],"which":[41],"is":[42],"problematic":[43],"since":[44],"softness":[46,81],"for":[50],"different":[51],"types":[52],"words":[54,57],"(e.g.":[55],"content":[56],"and":[58,96,107,110,129],"function":[59],"words)":[60],"should":[61],"differ.":[62],"Therefore,":[63],"we":[64],"propose":[65],"a":[66,70],"new":[67],"called":[72],"Self-Adaptive":[73],"Control":[74],"Temperature":[76],"(SACT)":[77],"to":[78,120],"control":[79],"by":[84],"means":[85],"temperature.":[89],"Experimental":[90],"results":[91],"Chinese-English":[94],"translation":[95,98,132],"English-Vietnamese":[97],"demonstrate":[99],"that":[100,115],"our":[101,116],"outperforms":[103],"baseline":[105],"models,":[106],"analysis":[109],"case":[112],"study":[113],"show":[114],"can":[118],"attend":[119],"most":[122],"relevant":[123],"elements":[124],"in":[125],"source-side":[127],"contexts":[128],"generate":[130],"high":[134],"quality.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}