{"id":"https://openalex.org/W2988435740","doi":"https://doi.org/10.1109/taslp.2019.2944078","title":"Low-Rank and Locality Constrained Self-Attention for Sequence Modeling","display_name":"Low-Rank and Locality Constrained Self-Attention for Sequence Modeling","publication_year":2019,"publication_date":"2019-11-11","ids":{"openalex":"https://openalex.org/W2988435740","doi":"https://doi.org/10.1109/taslp.2019.2944078","mag":"2988435740"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2944078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944078","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/A5101481141","display_name":"Qipeng Guo","orcid":"https://orcid.org/0000-0002-8805-8789"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qipeng Guo","raw_affiliation_strings":["School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8805-8789","affiliations":[{"raw_affiliation_string":"School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","raw_affiliation_strings":["School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7163-5247","affiliations":[{"raw_affiliation_string":"School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4897-9209","affiliations":[{"raw_affiliation_string":"School of Computer Science and the Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100459130","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0002-6277-0305"},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I3132425485","display_name":"Shanghai American School","ror":"https://ror.org/03xzda142","country_code":"CN","type":"education","lineage":["https://openalex.org/I3132425485"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["AWS Shanghai AI Lab, Shanghai, China","NYU Shanghai, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I3132425485","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"NYU Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I258800397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":2.3697,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.91152946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"2213","last_page":"2222"},"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":0.9955000281333923,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9950000047683716,"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/locality","display_name":"Locality","score":0.8265492916107178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742863893508911},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5634199380874634},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5612272620201111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543236494064331},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46011167764663696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41469606757164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34348559379577637},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3385741710662842},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12437179684638977}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8265492916107178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742863893508911},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5634199380874634},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5612272620201111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543236494064331},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46011167764663696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41469606757164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34348559379577637},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3385741710662842},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12437179684638977},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2944078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944078","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":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4666185321","display_name":null,"funder_award_id":"16JC1420401","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4918981142","display_name":null,"funder_award_id":"61751201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6449467950","display_name":null,"funder_award_id":"17JC1404100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6564481282","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u7684\u7aef\u5230\u7aef\u81ea\u52a8\u95ee\u7b54\u7cfb\u7edf\u7814\u7a76","funder_award_id":"61672162","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1816079941","https://openalex.org/W1840435438","https://openalex.org/W1984764846","https://openalex.org/W2114719613","https://openalex.org/W2126185232","https://openalex.org/W2158600149","https://openalex.org/W2168903001","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2252123671","https://openalex.org/W2267186426","https://openalex.org/W2308720496","https://openalex.org/W2338966855","https://openalex.org/W2415204069","https://openalex.org/W2556468274","https://openalex.org/W2557168633","https://openalex.org/W2593833795","https://openalex.org/W2756386045","https://openalex.org/W2795247881","https://openalex.org/W2888481121","https://openalex.org/W2896457183","https://openalex.org/W2899423466","https://openalex.org/W2962685628","https://openalex.org/W2962729168","https://openalex.org/W2962739339","https://openalex.org/W2962853227","https://openalex.org/W2962897020","https://openalex.org/W2963241825","https://openalex.org/W2963336685","https://openalex.org/W2963341956","https://openalex.org/W2963355447","https://openalex.org/W2963403868","https://openalex.org/W2963497309","https://openalex.org/W2963580443","https://openalex.org/W2963719234","https://openalex.org/W2963756346","https://openalex.org/W2963918774","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964189376","https://openalex.org/W2964302946","https://openalex.org/W4302343710","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6678723247","https://openalex.org/W6691329670","https://openalex.org/W6691459498","https://openalex.org/W6703363821","https://openalex.org/W6715743342","https://openalex.org/W6739901393","https://openalex.org/W6742080785","https://openalex.org/W6743583902","https://openalex.org/W6744649695","https://openalex.org/W6745360642","https://openalex.org/W6749845547","https://openalex.org/W6753780655","https://openalex.org/W6755207826","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W4234091740","https://openalex.org/W3162204513","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2022275305","https://openalex.org/W1604115909","https://openalex.org/W2369125128"],"abstract_inverted_index":{"Self-attention":[0],"mechanism":[1,25,104],"becomes":[2],"more":[3,5,141],"and":[4,44,77,89,97,108,124],"popular":[6],"in":[7],"natural":[8],"language":[9],"processing":[10],"(NLP)":[11],"applications.":[12],"Recent":[13],"studies":[14],"show":[15,117],"the":[16,23,52,63,71,94,102,106,121],"Transformer":[17,123],"architecture":[18],"which":[19],"relies":[20],"mainly":[21],"on":[22,29,46,112,128,134],"attention":[24,96,99],"achieves":[26],"much":[27],"success":[28],"large":[30],"datasets.":[31,49,131],"But":[32],"a":[33,135,140],"raised":[34],"problem":[35,76],"is":[36,40],"its":[37,58],"generalization":[38],"ability":[39],"weaker":[41],"than":[42],"CNN":[43],"RNN":[45],"many":[47],"moderate-sized":[48],"We":[50,91],"think":[51],"reason":[53],"can":[54],"be":[55],"attributed":[56],"to":[57,100],"unsuitable":[59],"inductive":[60],"bias":[61],"of":[62,144,147],"self-attention":[64,72,81,103,126],"structure.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"regard":[70],"as":[73],"matrix":[74],"decomposition":[75],"propose":[78],"an":[79],"improved":[80],"module":[82],"by":[83],"introducing":[84],"two":[85],"linguistic":[86],"constraints:":[87],"low-rank":[88,95,107],"locality.":[90],"further":[92],"develop":[93],"band":[98],"parameterize":[101],"under":[105],"locality":[109],"constraints.":[110],"Experiments":[111],"several":[113],"real":[114],"NLP":[115],"tasks":[116],"our":[118],"model":[119],"outperforms":[120],"vanilla":[122],"other":[125],"models":[127],"moderate":[129],"size":[130],"Additionally,":[132],"evaluation":[133],"synthetic":[136],"task":[137],"gives":[138],"us":[139],"detailed":[142],"understanding":[143],"working":[145],"mechanisms":[146],"different":[148],"architectures.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}