{"id":"https://openalex.org/W2903268415","doi":"https://doi.org/10.1109/taslp.2018.2883740","title":"Attention With Sparsity Regularization for Neural Machine Translation and Summarization","display_name":"Attention With Sparsity Regularization for Neural Machine Translation and Summarization","publication_year":2018,"publication_date":"2018-11-28","ids":{"openalex":"https://openalex.org/W2903268415","doi":"https://doi.org/10.1109/taslp.2018.2883740","mag":"2903268415"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2883740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2883740","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/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5293-7434","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992618","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-1028-3406"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327720","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-2368-7541"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2368-7541","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100319572"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":4.2306,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95356635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"27","issue":"3","first_page":"507","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8497288227081299},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7561725974082947},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6327930688858032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5967400074005127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5338695049285889},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44959205389022827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38101711869239807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32685327529907227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32254767417907715}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8497288227081299},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7561725974082947},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6327930688858032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967400074005127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338695049285889},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44959205389022827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38101711869239807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32685327529907227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32254767417907715}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2883740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2883740","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":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6753692345","display_name":null,"funder_award_id":"61673380","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":74,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1411230545","https://openalex.org/W1514535095","https://openalex.org/W1544827683","https://openalex.org/W1821462560","https://openalex.org/W1902237438","https://openalex.org/W2043995994","https://openalex.org/W2064675550","https://openalex.org/W2096175520","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2127529447","https://openalex.org/W2133564696","https://openalex.org/W2145494108","https://openalex.org/W2146502635","https://openalex.org/W2152553986","https://openalex.org/W2154652894","https://openalex.org/W2156985047","https://openalex.org/W2253795368","https://openalex.org/W2293363371","https://openalex.org/W2467173223","https://openalex.org/W2522143790","https://openalex.org/W2525778437","https://openalex.org/W2527845440","https://openalex.org/W2547875792","https://openalex.org/W2574535369","https://openalex.org/W2576713500","https://openalex.org/W2606974598","https://openalex.org/W2609482285","https://openalex.org/W2613904329","https://openalex.org/W2619122421","https://openalex.org/W2740984755","https://openalex.org/W2949615363","https://openalex.org/W2952138241","https://openalex.org/W2962784628","https://openalex.org/W2962834107","https://openalex.org/W2962867687","https://openalex.org/W2962965405","https://openalex.org/W2963062480","https://openalex.org/W2963123301","https://openalex.org/W2963260202","https://openalex.org/W2963333747","https://openalex.org/W2963403868","https://openalex.org/W2963443217","https://openalex.org/W2963463964","https://openalex.org/W2963502387","https://openalex.org/W2963598809","https://openalex.org/W2963699608","https://openalex.org/W2963929190","https://openalex.org/W2963991316","https://openalex.org/W2964165364","https://openalex.org/W2964265128","https://openalex.org/W3102307539","https://openalex.org/W4385245566","https://openalex.org/W6608792757","https://openalex.org/W6628501728","https://openalex.org/W6630875275","https://openalex.org/W6632455782","https://openalex.org/W6638523607","https://openalex.org/W6674650171","https://openalex.org/W6679434410","https://openalex.org/W6681435938","https://openalex.org/W6681588610","https://openalex.org/W6682631176","https://openalex.org/W6691766336","https://openalex.org/W6726804950","https://openalex.org/W6727690538","https://openalex.org/W6729448088","https://openalex.org/W6731948947","https://openalex.org/W6732407784","https://openalex.org/W6737778391","https://openalex.org/W6738577479","https://openalex.org/W6741937225","https://openalex.org/W6750968703"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W4284703357","https://openalex.org/W2775554247","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"The":[0],"attention":[1,63,81,91,130,148,164],"mechanism":[2,77],"has":[3],"become":[4],"the":[5,31,43,62,103,129,153,157,162],"<italic":[6],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[7,113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">de":[8],"facto</i>":[9],"standard":[10],"component":[11],"in":[12,30,42,93],"neural":[13,137],"sequence":[14,16],"to":[15,55,78,101,127],"tasks,":[17],"such":[18],"as":[19],"machine":[20,138],"translation":[21,139],"and":[22,61,69,119,140,169],"abstractive":[23,141],"summarization.":[24],"It":[25],"dynamically":[26],"determines":[27],"which":[28,94,125],"parts":[29],"input":[32,50],"sentence":[33],"should":[34,52,66],"be":[35,53,67],"focused":[36],"on":[37,135],"when":[38],"generating":[39],"each":[40,57],"word":[41],"output":[44],"sequence.":[45],"Ideally,":[46],"only":[47],"few":[48],"relevant":[49],"words":[51],"attended":[54],"at":[56],"decoding":[58],"time":[59],"step":[60],"weight":[64,82,131],"distribution":[65,165],"sparse":[68,90,147,168],"sharp.":[70,170],"However,":[71],"previous":[72],"methods":[73],"have":[74],"no":[75],"good":[76],"control":[79],"this":[80,85],"distribution.":[83,132],"In":[84],"paper,":[86],"we":[87],"propose":[88],"a":[89,95],"model":[92,149],"sparsity":[96],"regularization":[97,118],"term":[98],"is":[99],"designed":[100],"augment":[102],"objective":[104],"function.":[105],"We":[106],"explore":[107],"two":[108],"kinds":[109],"of":[110,124],"regularizations:":[111],"<inline-formula":[112],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[114],"notation=\"LaTeX\">$L_{\\infty":[115],"}$</tex-math></inline-formula>":[116],"-norm":[117],"minimum":[120],"entropy":[121],"regularization,":[122],"both":[123,136],"aim":[126],"sharpen":[128],"Extensive":[133],"experiments":[134],"summarization":[142],"demonstrate":[143],"that":[144,161],"our":[145],"proposed":[146],"can":[150],"substantially":[151],"outperform":[152],"strong":[154],"baselines.":[155],"And":[156],"detailed":[158],"analyses":[159],"reveal":[160],"final":[163],"indeed":[166],"becomes":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}