{"id":"https://openalex.org/W3119760890","doi":"https://doi.org/10.1109/ialp51396.2020.9310460","title":"Enhancing Attention Models via Multi-head Collaboration","display_name":"Enhancing Attention Models via Multi-head Collaboration","publication_year":2020,"publication_date":"2020-12-04","ids":{"openalex":"https://openalex.org/W3119760890","doi":"https://doi.org/10.1109/ialp51396.2020.9310460","mag":"3119760890"},"language":"en","primary_location":{"id":"doi:10.1109/ialp51396.2020.9310460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp51396.2020.9310460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120314022","display_name":"Huadong Wang","orcid":"https://orcid.org/0009-0000-4645-628X"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huadong Wang","raw_affiliation_strings":["Samsung Research China - Beijing (SRC-B), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research China - Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108647194","display_name":"Mei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Tu","raw_affiliation_strings":["Samsung Research China - Beijing (SRC-B), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research China - Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120314022"],"corresponding_institution_ids":["https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.52092156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8089955449104309},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.7258784770965576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.561438798904419},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5452911257743835},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5443278551101685},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5022270679473877},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.4864232540130615},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4761364758014679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09843826293945312},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06584697961807251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089955449104309},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.7258784770965576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.561438798904419},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5452911257743835},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5443278551101685},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5022270679473877},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.4864232540130615},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4761364758014679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09843826293945312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06584697961807251},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp51396.2020.9310460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp51396.2020.9310460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2070246124","https://openalex.org/W2251939518","https://openalex.org/W2308720496","https://openalex.org/W2525778437","https://openalex.org/W2613904329","https://openalex.org/W2755806193","https://openalex.org/W2896457183","https://openalex.org/W2934032625","https://openalex.org/W2934842096","https://openalex.org/W2945059185","https://openalex.org/W2949193663","https://openalex.org/W2950023669","https://openalex.org/W2951025380","https://openalex.org/W2952028139","https://openalex.org/W2952339051","https://openalex.org/W2962822108","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963925437","https://openalex.org/W2964082993","https://openalex.org/W2964110616","https://openalex.org/W2964265128","https://openalex.org/W2964347512","https://openalex.org/W2970726176","https://openalex.org/W2983902802","https://openalex.org/W2988309730","https://openalex.org/W2998547639","https://openalex.org/W3034939458","https://openalex.org/W3204406378","https://openalex.org/W4293718192","https://openalex.org/W4295253143","https://openalex.org/W4385245566","https://openalex.org/W6691459498","https://openalex.org/W6732520560","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6744788313","https://openalex.org/W6748546225","https://openalex.org/W6751097180","https://openalex.org/W6755207826","https://openalex.org/W6761311320","https://openalex.org/W6764072591","https://openalex.org/W6770605882","https://openalex.org/W6802243670"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Neural":[0],"attention":[1,17,24,36,49,54,84,97,116],"based":[2],"models":[3],"have":[4,91],"recently":[5],"boosted":[6],"performance":[7,113],"on":[8],"various":[9],"NLP":[10,121],"tasks.":[11],"Compared":[12],"with":[13,99],"single-head":[14],"attention,":[15],"multi-head":[16,48,115,135],"is":[18],"more":[19],"powerful":[20],"and":[21,33,123],"popular.":[22],"Multi-head":[23],"independently":[25],"attend":[26],"to":[27,63,78,90,94],"information":[28],"from":[29],"different":[30,83,88],"feature":[31],"subspaces":[32],"generates":[34],"multiple":[35],"distributions.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,71],"make":[42],"an":[43],"assumption":[44],"that":[45,105],"the":[46,80,92,112,124,129,132],"current":[47],"method":[50,77,108],"can":[51,109],"generate":[52],"complementary":[53],"distributions,":[55],"but":[56,75],"these":[57],"distributions":[58],"may":[59],"not":[60],"collaborate":[61],"properly":[62],"improve":[64,111],"prediction":[65],"quality.":[66],"To":[67],"validate":[68],"our":[69,106],"assumption,":[70],"propose":[72],"a":[73,118],"simple":[74],"effective":[76],"enhance":[79],"collaboration":[81],"of":[82,114,120,131,134],"heads,":[85],"which":[86],"allows":[87],"heads":[89],"chance":[93],"rectify":[95],"their":[96],"scores":[98],"other":[100],"heads.":[101],"Empirical":[102],"study":[103],"shows":[104],"proposed":[107],"significantly":[110],"over":[117],"range":[119],"tasks,":[122],"experimental":[125],"results":[126],"also":[127],"prove":[128],"existence":[130],"problem":[133],"collaboration.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}