{"id":"https://openalex.org/W2946068894","doi":"https://doi.org/10.18653/v1/p19-1555","title":"Soft Contextual Data Augmentation for Neural Machine Translation","display_name":"Soft Contextual Data Augmentation for Neural Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2946068894","doi":"https://doi.org/10.18653/v1/p19-1555","mag":"2946068894"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1555","pdf_url":"https://www.aclweb.org/anthology/P19-1555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1555.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101652490","display_name":"Fei Gao","orcid":"https://orcid.org/0009-0001-8729-9126"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences;"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028284977","display_name":"Jinhua Zhu","orcid":"https://orcid.org/0000-0003-2157-9077"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":["University of Science and Technology of China,"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Sun Yat-sen University,"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021772140","display_name":"Yingce Xia","orcid":"https://orcid.org/0000-0001-9823-9033"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingce Xia","raw_affiliation_strings":["Microsoft Reserach Asia;"],"affiliations":[{"raw_affiliation_string":"Microsoft Reserach Asia;","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Reserach Asia;"],"affiliations":[{"raw_affiliation_string":"Microsoft Reserach Asia;","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036544715","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0009-0009-3990-4414"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences;"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China,"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Reserach Asia;"],"affiliations":[{"raw_affiliation_string":"Microsoft Reserach Asia;","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101652490"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":10.29238895,"has_fulltext":true,"cited_by_count":116,"citation_normalized_percentile":{"value":0.9831765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5539","last_page":"5544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8431458473205566},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7735145688056946},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7495733499526978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7009660005569458},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6217905282974243},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5464141368865967},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5332071185112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35565075278282166},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10723963379859924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431458473205566},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7735145688056946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7495733499526978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7009660005569458},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6217905282974243},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5464141368865967},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5332071185112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35565075278282166},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10723963379859924},{"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:10.18653/v1/p19-1555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1555","pdf_url":"https://www.aclweb.org/anthology/P19-1555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1555","pdf_url":"https://www.aclweb.org/anthology/P19-1555.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946068894.pdf","grobid_xml":"https://content.openalex.org/works/W2946068894.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1915251500","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2163605009","https://openalex.org/W2250473257","https://openalex.org/W2546938941","https://openalex.org/W2594978815","https://openalex.org/W2613904329","https://openalex.org/W2765961751","https://openalex.org/W2766182427","https://openalex.org/W2804047946","https://openalex.org/W2886095922","https://openalex.org/W2888519496","https://openalex.org/W2905266130","https://openalex.org/W2950359962","https://openalex.org/W2952148143","https://openalex.org/W2956130159","https://openalex.org/W2962784628","https://openalex.org/W2962824887","https://openalex.org/W2963216553","https://openalex.org/W2963403868","https://openalex.org/W2963545917","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W3098341425","https://openalex.org/W4295727797","https://openalex.org/W4298393544","https://openalex.org/W4307459710","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W2349784553","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2146114872","https://openalex.org/W3022596247","https://openalex.org/W2392060890","https://openalex.org/W2601444686","https://openalex.org/W1997182898"],"abstract_inverted_index":{"While":[0],"data":[1,36,154],"augmentation":[2,37,45,141],"is":[3,25],"an":[4],"important":[5],"trick":[6],"to":[7,129],"boost":[8],"the":[9,82,97,101,116,123,127,157],"accuracy":[10],"of":[11,74,85,103,110,118,126,159],"deep":[12],"learning":[13],"methods":[14,46],"in":[15,21,57,67],"computer":[16],"vision":[17],"tasks,":[18],"its":[19,71],"study":[20],"natural":[22],"language":[23,94],"tasks":[24],"still":[26],"very":[27],"limited.":[28],"In":[29],"this":[30,104],"paper,":[31],"we":[32,60,80],"present":[33],"a":[34,58,63,68,86,89,93,107],"novel":[35],"method":[38,161],"for":[39],"neural":[40],"machine":[41,152],"translation.Different":[42],"from":[43],"previous":[44,140],"that":[47],"randomly":[48,64],"drop,":[49],"swap":[50],"or":[51],"replace":[52,81],"words":[53,56,120],"with":[54],"other":[55],"sentence,":[59],"softly":[61],"augment":[62],"chosen":[65],"word":[66,87,105,128],"sentence":[69],"by":[70,88,92,106],"contextual":[72,124],"mixture":[73],"multiple":[75,111],"related":[76],"words.":[77,114],"More":[78],"accurately,":[79],"one-hot":[83],"representation":[84],"distribution":[90],"(provided":[91],"model)":[95],"over":[96,162],"vocabulary,":[98],"i.e.,":[99],"replacing":[100],"embedding":[102],"weighted":[108],"combination":[109],"semantically":[112],"similar":[113],"Since":[115],"weights":[117],"those":[119],"depend":[121],"on":[122,145],"information":[125,138],"be":[130],"replaced,the":[131],"newly":[132],"generated":[133],"sentences":[134],"capture":[135],"much":[136],"richer":[137],"than":[139],"methods.":[142],"Experimental":[143],"results":[144],"both":[146],"small":[147],"scale":[148,151],"and":[149],"large":[150],"translation":[153],"sets":[155],"demonstrate":[156],"superiority":[158],"our":[160],"strong":[163],"baselines.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":4}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}