{"id":"https://openalex.org/W4408355331","doi":"https://doi.org/10.1109/icassp49660.2025.10889370","title":"Non-Autoregressive Multimodal Machine Translation","display_name":"Non-Autoregressive Multimodal Machine Translation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355331","doi":"https://doi.org/10.1109/icassp49660.2025.10889370"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889370","doi":"https://doi.org/10.1109/icassp49660.2025.10889370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889370","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5086239601","display_name":"Guojing Liu","orcid":"https://orcid.org/0000-0001-5494-8559","observed_orcids":["https://orcid.org/0000-0001-5494-8559"]},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojing Liu","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100982674","display_name":"Xiangqian Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangqian Ding","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108059798","display_name":"Huili Gong","orcid":"https://orcid.org/0000-0001-8691-0264","observed_orcids":["https://orcid.org/0000-0001-8691-0264","https://orcid.org/0000-0001-9829-1608"]},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huili Gong","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034777556","display_name":"Xiangyu Qu","orcid":"https://orcid.org/0009-0008-4478-398X","observed_orcids":["https://orcid.org/0009-0008-4478-398X","https://orcid.org/0009-0002-1471-4373"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Qu","raw_affiliation_strings":["Shandong University,School of Cyber Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Cyber Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433331","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0000-0002-8199-2720","observed_orcids":["https://orcid.org/0000-0002-8199-2720"]},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Yang","raw_affiliation_strings":["Qilu University of Technology,Shandong Academy of Sciences,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Academy of Sciences,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kai Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405278911","display_name":"Laiwu Vocational and Technical College","ror":"https://ror.org/00re8ag58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405278911"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yan","raw_affiliation_strings":["Laiwu Vocational and Technical College,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laiwu Vocational and Technical College,Jinan,China","institution_ids":["https://openalex.org/I4405278911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03593596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5121999979019165,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5121999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4666000008583069,"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/T10759","display_name":"Translation Studies and Practices","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/non-autoregressive-machine-translation","display_name":"non-autoregressive machine translation","score":0.828000009059906},{"id":"https://openalex.org/keywords/multimodal-machine-translation","display_name":"multimodal machine translation","score":0.996999979019165},{"id":"https://openalex.org/keywords/image-to-text-translation","display_name":"image-to-text translation","score":0.5199999809265137},{"id":"https://openalex.org/keywords/inference-acceleration","display_name":"inference acceleration","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7284203767776489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114737629890442},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6510409712791443},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.591172456741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934157431125641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36503681540489197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32091274857521057},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.16065850853919983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12549510598182678},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889370","doi":"https://doi.org/10.1109/icassp49660.2025.10889370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889370","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W2007662413","https://openalex.org/W2032175749","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2513263213","https://openalex.org/W2581101319","https://openalex.org/W2745132836","https://openalex.org/W2767206889","https://openalex.org/W2804243936","https://openalex.org/W2888070626","https://openalex.org/W2933138175","https://openalex.org/W2950886580","https://openalex.org/W2963909453","https://openalex.org/W3034871396","https://openalex.org/W3083614545","https://openalex.org/W3175665465","https://openalex.org/W3176395632","https://openalex.org/W3207410886","https://openalex.org/W4226167525","https://openalex.org/W4226315594","https://openalex.org/W4280567072","https://openalex.org/W4312471667","https://openalex.org/W4324325910","https://openalex.org/W4385245566","https://openalex.org/W4392903003","https://openalex.org/W4392903122","https://openalex.org/W4393160064","https://openalex.org/W6839745749","https://openalex.org/W7133215650","https://openalex.org/W7133231481"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","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":{"Performing":[0],"better":[1],"text":[2],"translation":[3,24,68,77,131],"by":[4],"integrating":[5],"auxiliary":[6],"inputs":[7],"from":[8],"visual":[9,95],"information":[10],"has":[11],"gained":[12],"widespread":[13],"attention":[14,112],"in":[15,38,83],"recent":[16],"years.":[17],"While":[18],"existing":[19],"methods":[20],"outperform":[21],"the":[22,26,31,46,66,76,81,88,118,126,137],"text-only":[23],"models,":[25],"step-by-step":[27],"generative":[28,67,119],"style":[29],"reduces":[30],"inference":[32],"speed,":[33],"which":[34,64,139],"limits":[35],"their":[36],"applicability":[37],"real-world":[39],"scenarios.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,57,79],"propose":[45],"non-autoregressive":[47],"language":[48],"model":[49],"(NA-LM)":[50],"for":[51,113],"multimodal":[52,72,114],"machine":[53],"translation.":[54],"With":[55],"NA-LM,":[56],"develop":[58],"a":[59,70,91],"Non-Autoregressive":[60],"Multimodal":[61],"Transformer":[62],"(NA-MMT),":[63],"accelerates":[65],"via":[69],"parallel":[71],"decoder.":[73],"To":[74],"retain":[75],"performance,":[78],"improve":[80],"NA-MMT":[82,127],"twofold:":[84],"1)":[85],"We":[86,105],"preprocess":[87],"image":[89],"into":[90],"refined":[92],"sequence":[93],"of":[94],"entities":[96],"with":[97,132],"length":[98],"encoding":[99],"to":[100,116],"reduce":[101],"irrelevant":[102],"information;":[103],"2)":[104],"design":[106],"cross":[107],"fertility":[108],"and":[109],"cross-modal":[110],"gate":[111],"decoder":[115],"enhance":[117],"quality.":[120],"Experiments":[121],"on":[122],"Multi30k":[123],"datasets":[124],"show":[125],"can":[128],"generate":[129],"high-quality":[130],"over":[133],"11\u00d7":[134],"speedup":[135],"than":[136],"baselines,":[138],"is":[140],"strongly":[141],"competitive.":[142]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
