{"id":"https://openalex.org/W4390187104","doi":"https://doi.org/10.1109/access.2023.3346952","title":"BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints","display_name":"BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints","publication_year":2023,"publication_date":"2023-12-25","ids":{"openalex":"https://openalex.org/W4390187104","doi":"https://doi.org/10.1109/access.2023.3346952"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3346952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3346952","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10373869.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10373869.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091453488","display_name":"Mohammad Golam Sohrab","orcid":"https://orcid.org/0000-0001-5540-7834"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mohammad Golam Sohrab","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5540-7834","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045914141","display_name":"Masaki Asada","orcid":"https://orcid.org/0000-0002-7117-5962"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Asada","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7117-5962","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034561278","display_name":"Mat\u012bss Rikters","orcid":"https://orcid.org/0000-0002-3530-6873"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mat\u012bss Rikters","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101412540","display_name":"Makoto Miwa","orcid":"https://orcid.org/0000-0002-2330-6972"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Makoto Miwa","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","Toyota Technological Institute, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Toyota Technological Institute, Japan","institution_ids":["https://openalex.org/I4840577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091453488"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.0221,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89619184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"23","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T13629","display_name":"Text Readability and Simplification","score":0.9728999733924866,"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":0.83370041847229},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8220394849777222},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.798274040222168},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.706904411315918},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.637535810470581},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.617099404335022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5950852036476135},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5617269277572632},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4985051155090332},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.48737937211990356},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4838341772556305},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4474489688873291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4268607199192047},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42044854164123535},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.41800352931022644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41430145502090454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34067603945732117},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3226395845413208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2188662588596344},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20292973518371582},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0770515501499176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83370041847229},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8220394849777222},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.798274040222168},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.706904411315918},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.637535810470581},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.617099404335022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5950852036476135},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5617269277572632},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4985051155090332},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.48737937211990356},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4838341772556305},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4474489688873291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4268607199192047},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42044854164123535},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.41800352931022644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41430145502090454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34067603945732117},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3226395845413208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2188662588596344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20292973518371582},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0770515501499176},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3346952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3346952","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10373869.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a335ee9967c840cc815b66b50cc44d11","is_oa":true,"landing_page_url":"https://doaj.org/article/a335ee9967c840cc815b66b50cc44d11","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 23-33 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3346952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3346952","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10373869.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6725152017","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390187104.pdf","grobid_xml":"https://content.openalex.org/works/W4390187104.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2157331557","https://openalex.org/W2888482885","https://openalex.org/W2892213699","https://openalex.org/W2923014074","https://openalex.org/W2962717047","https://openalex.org/W2963434219","https://openalex.org/W2963532001","https://openalex.org/W2963736842","https://openalex.org/W2963748441","https://openalex.org/W2979826702","https://openalex.org/W2988975212","https://openalex.org/W2996843693","https://openalex.org/W3034999214","https://openalex.org/W3036120435","https://openalex.org/W3098708719","https://openalex.org/W3100439847","https://openalex.org/W3177172118","https://openalex.org/W3200578235","https://openalex.org/W4212774754","https://openalex.org/W4288089799","https://openalex.org/W4385570271","https://openalex.org/W4385572691","https://openalex.org/W6638523607","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6755207826","https://openalex.org/W6762471145","https://openalex.org/W6762521896","https://openalex.org/W6763701032","https://openalex.org/W6767737316","https://openalex.org/W6769627184","https://openalex.org/W6789821389"],"related_works":["https://openalex.org/W3034800807","https://openalex.org/W4287758468","https://openalex.org/W3035130722","https://openalex.org/W4310731959","https://openalex.org/W3034878914","https://openalex.org/W2044732683","https://openalex.org/W3019688513","https://openalex.org/W2386843486","https://openalex.org/W3092480528","https://openalex.org/W1988325139"],"abstract_inverted_index":{"We":[0,57,108],"introduce":[1],"BERT-NAR-BERT":[2],"(BnB)":[3],"\u2013":[4,72],"a":[5,61],"pre-trained":[6],"non-autoregressive":[7],"sequence-to-sequence":[8],"model,":[9],"which":[10],"employs":[11],"BERT":[12],"as":[13],"the":[14,17,29,42,52,117],"backbone":[15],"for":[16,21],"encoder":[18],"and":[19,25,31,45,68,77],"decoder":[20],"natural":[22,63],"language":[23,64],"understanding":[24,65],"generation":[26,70],"tasks.":[27],"During":[28],"pre-training":[30],"fine-tuning":[32],"with":[33,92,116],"BERT-NAR-BERT,":[34],"two":[35],"challenging":[36],"aspects":[37],"are":[38],"considered":[39],"by":[40],"adopting":[41],"length":[43,54],"classification":[44,48],"connectionist":[46],"temporal":[47],"models":[49],"to":[50,101,110],"control":[51],"output":[53,97],"of":[55,120],"BnB.":[56],"evaluate":[58],"it":[59],"using":[60],"standard":[62],"benchmark":[66],"GLUE":[67],"three":[69],"tasks":[71],"abstractive":[73],"summarization,":[74],"question":[75],"generation,":[76],"machine":[78],"translation.":[79],"Our":[80],"results":[81],"show":[82],"substantial":[83],"improvements":[84],"in":[85,96],"inference":[86],"speed":[87],"(on":[88],"average":[89],"10x":[90],"faster)":[91],"only":[93],"little":[94],"deficiency":[95],"quality":[98],"when":[99],"compared":[100],"our":[102,112],"direct":[103],"autoregressive":[104],"baseline":[105],"BERT2BERT":[106],"model.":[107],"plan":[109],"release":[111],"code":[113],"on":[114],"GitHub":[115],"final":[118],"version":[119],"this":[121],"paper.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}