{"id":"https://openalex.org/W2984121220","doi":"https://doi.org/10.1145/3358414","title":"Layer-Wise De-Training and Re-Training for ConvS2S Machine Translation","display_name":"Layer-Wise De-Training and Re-Training for ConvS2S Machine Translation","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2984121220","doi":"https://doi.org/10.1145/3358414","mag":"2984121220"},"language":"en","primary_location":{"id":"doi:10.1145/3358414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358414","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3358414","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021224234","display_name":"Hongfei Yu","orcid":"https://orcid.org/0009-0003-7210-5581"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hongfei Yu","raw_affiliation_strings":["Soochow University"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049243695","display_name":"Xiaoqing Zhou","orcid":"https://orcid.org/0000-0002-4139-032X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqing Zhou","raw_affiliation_strings":["Soochow University"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089990864","display_name":"Xiangyu Duan","orcid":"https://orcid.org/0000-0002-7268-8823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Duan","raw_affiliation_strings":["Soochow University"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Soochow University"],"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021224234"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6655569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"19","issue":"2","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9944000244140625,"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/initialization","display_name":"Initialization","score":0.9495091438293457},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7841296195983887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586630582809448},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7230883836746216},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6350811719894409},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6308375000953674},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6262264251708984},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5677860975265503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5618981122970581},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5281279683113098},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37859439849853516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.127592533826828}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9495091438293457},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7841296195983887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586630582809448},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7230883836746216},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6350811719894409},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6308375000953674},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6262264251708984},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5677860975265503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618981122970581},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5281279683113098},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37859439849853516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.127592533826828},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3358414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358414","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3358414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3358414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3358414","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4761440921","display_name":null,"funder_award_id":"2016YFE0132100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7371885796","display_name":null,"funder_award_id":"61673289,61273319","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2984121220.pdf","grobid_xml":"https://content.openalex.org/works/W2984121220.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1581231885","https://openalex.org/W1815076433","https://openalex.org/W2095705004","https://openalex.org/W2100664567","https://openalex.org/W2101105183","https://openalex.org/W2107878631","https://openalex.org/W2194775991","https://openalex.org/W2540404261","https://openalex.org/W2552839021","https://openalex.org/W2613904329","https://openalex.org/W2621907989","https://openalex.org/W2626778328","https://openalex.org/W2760656271","https://openalex.org/W2899771611","https://openalex.org/W2930957955","https://openalex.org/W2949335953","https://openalex.org/W2949888546","https://openalex.org/W2952436057","https://openalex.org/W2962784628","https://openalex.org/W2962997665","https://openalex.org/W2963011474","https://openalex.org/W2964213727","https://openalex.org/W2964308564","https://openalex.org/W3023058184"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"The":[0],"convolutional":[1],"sequence-to-sequence":[2],"(ConvS2S)":[3],"machine":[4,13],"translation":[5,14,160],"system":[6],"is":[7,107],"one":[8,63],"of":[9,62,65,115],"the":[10,18,59,66,80,94,102,116,132,143,151,158],"typical":[11],"neural":[12],"(NMT)":[15],"systems.":[16],"Training":[17],"ConvS2S":[19,43,117,159],"model":[20,44,118],"tends":[21],"to":[22,39,51,83,126,142],"get":[23],"stuck":[24],"in":[25,29,45],"a":[26,41,46,53,88],"local":[27,133],"optimum":[28],"our":[30,154],"pre-studies.":[31],"To":[32],"overcome":[33],"this":[34],"inferior":[35],"behavior,":[36],"we":[37],"propose":[38],"de-train":[40],"trained":[42,60],"mild":[47],"way":[48],"and":[49,92,146,166],"retrain":[50],"find":[52],"better":[54,168],"solution":[55],"globally.":[56],"In":[57],"particular,":[58],"parameters":[61,76],"layer":[64,109,111],"NMT":[67],"network":[68],"are":[69,77,119],"abandoned":[70],"by":[71,110],"re-initialization":[72],"while":[73],"other":[74],"layers\u2019":[75],"kept":[78],"at":[79],"same":[81],"time":[82],"kick":[84],"off":[85],"re-optimization":[86],"from":[87,101,131],"new":[89,95],"start":[90,96],"point":[91,97],"safeguard":[93],"not":[98],"too":[99],"far":[100],"previous":[103],"optimum.":[104],"This":[105],"procedure":[106],"executed":[108],"until":[112],"all":[113],"layers":[114],"explored.":[120],"Experiments":[121],"show":[122],"that":[123],"when":[124],"compared":[125],"various":[127,163],"measures":[128],"for":[129],"escaping":[130],"optimum,":[134],"including":[135],"initialization":[136],"with":[137,150],"random":[138],"seeds,":[139],"adding":[140],"perturbations":[141],"baseline":[144,152],"parameters,":[145],"continuing":[147],"training":[148],"(con-training)":[149],"models,":[153],"method":[155],"consistently":[156],"improves":[157],"quality":[161],"across":[162],"language":[164],"pairs":[165],"achieves":[167],"performance.":[169]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}