{"id":"https://openalex.org/W4376166793","doi":"https://doi.org/10.48550/arxiv.2305.05226","title":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","display_name":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","publication_year":2023,"publication_date":"2023-05-09","ids":{"openalex":"https://openalex.org/W4376166793","doi":"https://doi.org/10.48550/arxiv.2305.05226"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.05226","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05226","pdf_url":"https://arxiv.org/pdf/2305.05226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.05226","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060187092","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0002-9367-5685"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ma, Cong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366785","display_name":"Yaping Zhang","orcid":"https://orcid.org/0009-0009-9295-1367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yaping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108647194","display_name":"Mei Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Mei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362748","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-0843-8202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zong, Chengqing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060187092"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9747999906539917,"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":0.9747999906539917,"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":0.9632999897003174,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9613999724388123,"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/pipeline","display_name":"Pipeline (software)","score":0.8619961738586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163077235221863},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7309704422950745},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6613038778305054},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6202487945556641},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6086735725402832},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6017307043075562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5764451026916504},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5546290278434753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4992082118988037},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4763781726360321},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47381913661956787},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.460529625415802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3601555824279785},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15881428122520447},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13362523913383484}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8619961738586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163077235221863},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7309704422950745},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6613038778305054},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6202487945556641},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6086735725402832},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6017307043075562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5764451026916504},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5546290278434753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4992082118988037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4763781726360321},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47381913661956787},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.460529625415802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601555824279785},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15881428122520447},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13362523913383484},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.05226","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05226","pdf_url":"https://arxiv.org/pdf/2305.05226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.05226","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.05226","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.05226","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05226","pdf_url":"https://arxiv.org/pdf/2305.05226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G4930465771","display_name":null,"funder_award_id":"62106265","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4376166793.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W3179968364","https://openalex.org/W4385572700","https://openalex.org/W2949968076","https://openalex.org/W2935811960","https://openalex.org/W2969407538","https://openalex.org/W2917049097"],"abstract_inverted_index":{"Text":[0],"image":[1,100,165],"machine":[2],"translation":[3,132,151,166],"(TIMT)":[4],"has":[5],"been":[6],"widely":[7],"used":[8],"in":[9,18,102],"various":[10],"real-world":[11],"applications,":[12],"which":[13],"translates":[14],"source":[15],"language":[16,23],"texts":[17],"images":[19],"into":[20,32,52,76],"another":[21],"target":[22],"sentence.":[24],"Existing":[25],"methods":[26],"on":[27],"TIMT":[28,79,97,105],"are":[29,88,125,145],"mainly":[30],"divided":[31],"two":[33],"categories:":[34],"the":[35,40,49,53,77,82,92,95,103,110,115,120,131,150,163],"recognition-then-translation":[36],"pipeline":[37,50,83,173,190],"model":[38,51,55,80,106],"and":[39,123,134,141,168,172,178,191],"end-to-end":[41,54,78,96,104,171,192],"model.":[42,84,98],"However,":[43],"how":[44],"to":[45,72,90,147],"transfer":[46],"knowledge":[47,75,111,129,143],"from":[48,81,114,130],"remains":[56],"an":[57],"unsolved":[58],"problem.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65],"novel":[66],"Multi-Teacher":[67],"Knowledge":[68],"Distillation":[69],"(MTKD)":[70],"method":[71],"effectively":[73,161],"distillate":[74],"Specifically,":[85],"three":[86],"teachers":[87],"utilized":[89],"improve":[91],"performance":[93,167],"of":[94,188],"The":[99],"encoder":[101,122],"is":[107],"optimized":[108],"with":[109,175],"distillation":[112],"guidance":[113],"recognition":[116],"teacher":[117,136],"encoder,":[118],"while":[119],"sequential":[121,133],"decoder":[124,135],"improved":[126],"by":[127],"transferring":[128],"models.":[137,193],"Furthermore,":[138],"both":[139,189],"token":[140],"sentence-level":[142],"distillations":[144],"incorporated":[146],"better":[148],"boost":[149],"performance.":[152],"Extensive":[153],"experimental":[154],"results":[155],"show":[156],"that":[157,183],"our":[158],"proposed":[159],"MTKD":[160,184],"improves":[162],"text":[164],"outperforms":[169],"existing":[170],"models":[174],"fewer":[176],"parameters":[177],"less":[179],"decoding":[180],"time,":[181],"illustrating":[182],"can":[185],"take":[186],"advantage":[187]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}