{"id":"https://openalex.org/W4377000448","doi":"https://doi.org/10.1109/taslp.2023.3277245","title":"Alleviating Exposure Bias for Neural Machine Translation via Contextual Augmentation and Self Distillation","display_name":"Alleviating Exposure Bias for Neural Machine Translation via Contextual Augmentation and Self Distillation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377000448","doi":"https://doi.org/10.1109/taslp.2023.3277245"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3277245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277245","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/A5035904541","display_name":"Zhidong Liu","orcid":"https://orcid.org/0000-0002-6553-4236"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidong Liu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6553-4236","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369260","display_name":"Junhui Li","orcid":"https://orcid.org/0000-0001-7829-6348"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Li","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7829-6348","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101923144","display_name":"Muhua Zhu","orcid":"https://orcid.org/0000-0002-6519-2379"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhua Zhu","raw_affiliation_strings":["Meituan Inc., Shanghai, China","Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-6519-2379","affiliations":[{"raw_affiliation_string":"Meituan Inc., Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77447082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2079","last_page":"2089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9943000078201294,"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/ground-truth","display_name":"Ground truth","score":0.8195198774337769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5713446140289307},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5570990443229675},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5371582508087158},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5316752791404724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520086407661438},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.44891270995140076},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4409744143486023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42474400997161865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.406112402677536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3996308743953705},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.2658627927303314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23874425888061523},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12069332599639893}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8195198774337769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5713446140289307},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5570990443229675},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5371582508087158},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5316752791404724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520086407661438},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.44891270995140076},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4409744143486023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42474400997161865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.406112402677536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3996308743953705},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2658627927303314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23874425888061523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12069332599639893},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3277245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277245","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","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5678221373","display_name":null,"funder_award_id":"61876120","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":69,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2081580037","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2170240176","https://openalex.org/W2176263492","https://openalex.org/W2250473257","https://openalex.org/W2251658415","https://openalex.org/W2594978815","https://openalex.org/W2803023299","https://openalex.org/W2890220768","https://openalex.org/W2896457183","https://openalex.org/W2935811960","https://openalex.org/W2944869267","https://openalex.org/W2946068894","https://openalex.org/W2962369866","https://openalex.org/W2962784628","https://openalex.org/W2962824887","https://openalex.org/W2963212250","https://openalex.org/W2963216553","https://openalex.org/W2963463964","https://openalex.org/W2963545917","https://openalex.org/W2964345285","https://openalex.org/W2965373594","https://openalex.org/W2971296908","https://openalex.org/W2978017171","https://openalex.org/W2979826702","https://openalex.org/W2987861506","https://openalex.org/W2999635570","https://openalex.org/W3004437239","https://openalex.org/W3006963874","https://openalex.org/W3035023562","https://openalex.org/W3089659770","https://openalex.org/W3101980583","https://openalex.org/W3128699722","https://openalex.org/W3191406681","https://openalex.org/W4285115391","https://openalex.org/W4287829148","https://openalex.org/W4295312788","https://openalex.org/W4298393544","https://openalex.org/W4385245566","https://openalex.org/W6608792757","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6685053522","https://openalex.org/W6685322675","https://openalex.org/W6734807902","https://openalex.org/W6739901393","https://openalex.org/W6745388339","https://openalex.org/W6745740328","https://openalex.org/W6751751081","https://openalex.org/W6755207826","https://openalex.org/W6765939562","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6768851824","https://openalex.org/W6774569510","https://openalex.org/W6774738212","https://openalex.org/W6783973398","https://openalex.org/W6787038602"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2949968076","https://openalex.org/W2935811960","https://openalex.org/W2969407538"],"abstract_inverted_index":{"In":[0],"neural":[1],"machine":[2],"translation":[3,180,208],"(NMT),":[4],"most":[5],"sequence-to-sequence":[6],"(seq2seq)":[7],"models":[8],"are":[9],"trained":[10],"only":[11,150],"with":[12],"the":[13,17,25,31,35,38,64,69,111,116,132,145,199,207],"teacher-forcing":[14],"paradigm,":[15],"where":[16],"ground":[18,27,50,55,77,122,151],"truth":[19,28,51,56,78,102,123,152],"history":[20,44,52,105],"is":[21],"used":[22],"to":[23,60,67,96,99,114,130,134,139,147],"predict":[24,148],"next":[26,39,108],"word.":[29],"At":[30],"inference":[32],"stage,":[33],"however,":[34],"decoder":[36],"predicts":[37],"token":[40],"solely":[41],"based":[42],"on":[43,164,191,205],"generated":[45],"from":[46],"scratch.":[47],"Both":[48],"using":[49,76],"and":[53,88,103,159,172],"predicting":[54,107,121],"words":[57],"potentially":[58,157],"lead":[59],"exposure":[61,72,117],"bias.":[62],"On":[63,110],"one":[65],"hand,":[66,113],"alleviate":[68,115],"issue":[70],"of":[71,90,201],"bias":[73,118],"caused":[74,119],"by":[75,84,120],"history,":[79],"we":[80,125],"propose":[81],"contextual":[82,93],"augmentation":[83,94],"allowing":[85],"substitution,":[86],"insertion,":[87],"deletion":[89],"words.":[91,109,161],"The":[92],"applies":[95],"target":[97],"sequence":[98],"generate":[100],"non-ground":[101],"natural":[104],"when":[106],"other":[112,156],"words,":[124,153],"further":[126,197],"apply":[127],"self":[128],"distillation":[129],"guide":[131],"model":[133,146],"carry":[135],"out":[136],"optimization":[137],"according":[138],"smoothed":[140],"prediction":[141],"distribution,":[142],"i.e,":[143],"enable":[144],"not":[149],"but":[154],"also":[155],"correct":[158],"reasonable":[160],"Experimental":[162],"results":[163],"WMT14":[165],"English":[166,179],"<inline-formula":[167,175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168,176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[169,177],"notation=\"LaTeX\">$\\leftrightarrow$</tex-math></inline-formula>":[170],"German":[171,174],"IWSLT14":[173],"notation=\"LaTeX\">$\\rightarrow$</tex-math></inline-formula>":[178],"tasks":[181],"demonstrate":[182],"that":[183],"our":[184,202],"approach":[185,204],"achieves":[186],"significant":[187],"improvements":[188],"over":[189],"Transformer":[190],"standard":[192],"benchmarks.":[193],"Detailed":[194],"experimental":[195],"analyses":[196],"reveal":[198],"effectiveness":[200],"proposed":[203],"improving":[206],"quality.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}