{"id":"https://openalex.org/W4386536192","doi":"https://doi.org/10.1109/taslp.2023.3313428","title":"Hiformer: Sequence Modeling Networks With Hierarchical Attention Mechanisms","display_name":"Hiformer: Sequence Modeling Networks With Hierarchical Attention Mechanisms","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386536192","doi":"https://doi.org/10.1109/taslp.2023.3313428"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313428","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486499","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-7698-6262"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-7698-6262","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377555","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-6780-4391"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-6780-4391","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tsinghua Shenzhen International Graduate School of Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School of Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-6725-1160","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-4427-3532","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9166,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79237208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3993","last_page":"4003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.8022251129150391},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7657071352005005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521370649337769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4781797230243683},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4619060158729553},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43578803539276123},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4332057535648346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38122498989105225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3545369505882263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.073418527841568}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8022251129150391},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7657071352005005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521370649337769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781797230243683},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4619060158729553},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43578803539276123},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4332057535648346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38122498989105225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3545369505882263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.073418527841568},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313428","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1494198834","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W2117671523","https://openalex.org/W2124807415","https://openalex.org/W2125336414","https://openalex.org/W2194775991","https://openalex.org/W2402146185","https://openalex.org/W2760379373","https://openalex.org/W2770970123","https://openalex.org/W2788330850","https://openalex.org/W2802023636","https://openalex.org/W2888520903","https://openalex.org/W2889048668","https://openalex.org/W2890964657","https://openalex.org/W2897983179","https://openalex.org/W2912351236","https://openalex.org/W2950621961","https://openalex.org/W2951166594","https://openalex.org/W2962784628","https://openalex.org/W2962883855","https://openalex.org/W2962931466","https://openalex.org/W2963149635","https://openalex.org/W2963216553","https://openalex.org/W2963542740","https://openalex.org/W2963652649","https://openalex.org/W2963735467","https://openalex.org/W2963829526","https://openalex.org/W2964110616","https://openalex.org/W2971351900","https://openalex.org/W2981857663","https://openalex.org/W2991213871","https://openalex.org/W3006381853","https://openalex.org/W3016010032","https://openalex.org/W3034742481","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3102816807","https://openalex.org/W3113395007","https://openalex.org/W3126721948","https://openalex.org/W3161365423","https://openalex.org/W3166456182","https://openalex.org/W3176913643","https://openalex.org/W4226380987","https://openalex.org/W4292779060","https://openalex.org/W4301371414","https://openalex.org/W4309041555","https://openalex.org/W4385245566","https://openalex.org/W6608792757","https://openalex.org/W6626481562","https://openalex.org/W6636688132","https://openalex.org/W6638273328","https://openalex.org/W6638749077","https://openalex.org/W6725939724","https://openalex.org/W6739901393","https://openalex.org/W6746261267","https://openalex.org/W6754473786","https://openalex.org/W6754919597","https://openalex.org/W6770506093","https://openalex.org/W6771713106","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6787294940","https://openalex.org/W6790307280","https://openalex.org/W6803547063"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W2963499882","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3098873988","https://openalex.org/W2949454572","https://openalex.org/W3066373881"],"abstract_inverted_index":{"The":[0],"attention-based":[1],"encoder-decoder":[2],"structure,":[3],"such":[4],"as":[5],"the":[6,27,35,45,79,82,102,110,116,139,160,163],"Transformer,":[7],"has":[8,48],"achieved":[9],"state-of-the-art":[10],"performance":[11],"on":[12,44,88,109,153],"various":[13,71],"sequence":[14,125],"modeling":[15,126],"tasks,e.g.,":[16],"machine":[17],"translation":[18],"(MT)":[19],"and":[20,59,91,104,141,156],"automatic":[21],"speech":[22],"recognition":[23],"(ASR),":[24],"benefited":[25],"from":[26,70],"superior":[28],"capability":[29],"of":[30,53,162],"layer-wise":[31],"self-attention":[32,80],"mechanism":[33],"in":[34,81],"encoder/decoder":[36],"to":[37,145],"access":[38],"long-distance":[39],"contextual":[40],"information.":[41],"Recently,":[42],"analysis":[43],"Transformer":[46,84],"layers":[47],"shown":[49],"that":[50,136],"different":[51,65],"levels":[52,72],"information,e.g.,":[54],"phoneme":[55],"level,":[56,61],"word":[57],"level":[58],"semantic":[60],"are":[62],"represented":[63],"at":[64],"layers.":[66,118],"Effectively":[67],"integrating":[68],"information":[69,97,144],"is":[73],"important":[74],"for":[75],"structured":[76,147],"prediction.":[77],"However,":[78],"conventional":[83],"structure":[85,127],"only":[86,107],"focuses":[87,108],"intra-layer":[89],"integration,":[90],"does":[92],"not":[93],"explicitly":[94],"model":[95],"inter-layer":[96,140],"relationships.":[98],"Also,":[99],"attention":[100,132],"across":[101],"encoder":[103,112],"decoder":[105],"(cross-coder)":[106],"top":[111],"layer":[113],"but":[114],"ignores":[115],"intermediate":[117],"In":[119],"this":[120],"paper,":[121],"we":[122],"propose":[123],"a":[124,130],"equipped":[128],"with":[129],"hierarchical":[131,143],"mechanism,":[133],"named":[134],"Hiformer,":[135],"can":[137],"consider":[138],"cross-coder":[142],"improve":[146],"prediction":[148],"performance.":[149],"Extensive":[150],"experiments":[151],"conducted":[152],"both":[154],"MT":[155],"ASR":[157],"tasks":[158],"demonstrate":[159],"effectiveness":[161],"proposed":[164],"Hiformer":[165],"model.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}