{"id":"https://openalex.org/W4407002324","doi":"https://doi.org/10.1007/s10462-025-11115-y","title":"Word embedding factor based multi-head attention","display_name":"Word embedding factor based multi-head attention","publication_year":2025,"publication_date":"2025-01-30","ids":{"openalex":"https://openalex.org/W4407002324","doi":"https://doi.org/10.1007/s10462-025-11115-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11115-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11115-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11115-y.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11115-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016933558","display_name":"Zhengren Li","orcid":"https://orcid.org/0000-0003-2908-2233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengren Li","raw_affiliation_strings":["School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591855","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0002-7482-3742"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Zhao","raw_affiliation_strings":["School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101405862","display_name":"Xiaohang Zhang","orcid":"https://orcid.org/0000-0003-2664-0877"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohang Zhang","raw_affiliation_strings":["School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102518561","display_name":"Huawei Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Han","raw_affiliation_strings":["School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102507737","display_name":"Cui Fen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui Huang","raw_affiliation_strings":["School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China"],"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing, 100876, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016933558"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":10.3814,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97475001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"58","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9912999868392944,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9905999898910522,"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":0.7896016836166382},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.6983694434165955},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6283103227615356},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6183940768241882},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5834664106369019},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5225224494934082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4578193426132202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41203612089157104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3972855806350708},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17350417375564575},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12411272525787354},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0725240409374237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896016836166382},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.6983694434165955},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6283103227615356},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6183940768241882},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5834664106369019},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5225224494934082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4578193426132202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41203612089157104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3972855806350708},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17350417375564575},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12411272525787354},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0725240409374237},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-025-11115-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11115-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11115-y.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11115-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11115-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11115-y.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3245652008","display_name":null,"funder_award_id":"72271034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407002324.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1840435438","https://openalex.org/W1970957579","https://openalex.org/W1994616650","https://openalex.org/W2008667434","https://openalex.org/W2011130150","https://openalex.org/W2023350458","https://openalex.org/W2030741364","https://openalex.org/W2035639136","https://openalex.org/W2047345533","https://openalex.org/W2066306397","https://openalex.org/W2085154044","https://openalex.org/W2085210515","https://openalex.org/W2097665571","https://openalex.org/W2118934859","https://openalex.org/W2144578941","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2267186426","https://openalex.org/W2919301453","https://openalex.org/W2923014074","https://openalex.org/W2946024010","https://openalex.org/W2978670439","https://openalex.org/W3105645800","https://openalex.org/W3119760890","https://openalex.org/W3131922516","https://openalex.org/W3145728363","https://openalex.org/W3150055540","https://openalex.org/W3154414470","https://openalex.org/W4224211827","https://openalex.org/W4289779195","https://openalex.org/W4294982692","https://openalex.org/W4309772397","https://openalex.org/W4310214223","https://openalex.org/W4312560592","https://openalex.org/W6818723395"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800","https://openalex.org/W4385432812"],"abstract_inverted_index":{"The":[0,84],"natural":[1],"language":[2],"processing":[3],"(NLP)":[4],"field":[5],"has":[6,117],"made":[7],"significant":[8,118],"progress":[9],"using":[10],"deep":[11],"learning":[12],"models":[13],"based":[14,42],"on":[15,43],"multi-head":[16],"attention":[17,65],"mechanisms,":[18],"such":[19],"as":[20],"Transformer":[21],"and":[22,46,56,81,94,109,134],"BERT.":[23],"However,":[24],"there":[25],"are":[26],"two":[27],"major":[28],"limitations":[29],"to":[30,99],"this":[31,59],"approach.":[32],"First,":[33],"the":[34,75,112],"number":[35],"of":[36,77,129],"heads":[37],"is":[38,49],"often":[39],"manually":[40],"set":[41],"empirical":[44],"experience,":[45],"second,":[47],"it":[48],"not":[50],"clear":[51],"enough":[52],"in":[53,127],"semantic":[54,106],"understanding":[55,107],"interpretation.":[57],"In":[58],"study,":[60],"we":[61],"propose":[62],"a":[63],"novel":[64],"mechanism":[66],"called":[67],"Factor":[68],"Analysis-based":[69],"Multi-head":[70],"(FAM)":[71],"Attention,":[72],"which":[73],"combines":[74],"theory":[76],"explorative":[78],"factor":[79],"analysis":[80],"word":[82],"embedding.":[83],"experimental":[85],"results":[86],"demonstrate":[87],"that":[88],"FAM":[89],"Attention":[90],"achieves":[91],"better":[92,105],"performance":[93],"requires":[95],"fewer":[96],"parameters":[97],"compared":[98],"traditional":[100],"methods":[101],"while":[102],"also":[103,116],"having":[104],"ability":[108],"interpretability":[110],"at":[111],"token":[113],"level.":[114],"This":[115],"implications":[119],"for":[120],"current":[121],"Large":[122],"Language":[123],"Models":[124],"(LLMs),":[125],"particularly":[126],"terms":[128],"effectively":[130],"reducing":[131],"parameter":[132],"counts":[133],"enhancing":[135],"performance.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}