{"id":"https://openalex.org/W2951476960","doi":"https://doi.org/10.18653/v1/p19-1579","title":"Generalized Data Augmentation for Low-Resource Translation","display_name":"Generalized Data Augmentation for Low-Resource Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951476960","doi":"https://doi.org/10.18653/v1/p19-1579","mag":"2951476960"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1579","doi":"https://doi.org/10.18653/v1/p19-1579","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1579","pdf_url":"https://www.aclweb.org/anthology/P19-1579.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/P19-1579.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003465314","display_name":"Mengzhou Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengzhou Xia","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109393622","display_name":"Xiang Kong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Kong","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X","observed_orcids":["https://orcid.org/0000-0002-8544-246X"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789","observed_orcids":["https://orcid.org/0000-0002-2072-3789"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":6.5959,"has_fulltext":true,"cited_by_count":111,"citation_normalized_percentile":{"value":0.97527677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5786","last_page":"5796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0027000000700354576,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0008999999845400453,"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/data-augmentation","display_name":"data augmentation","score":0.8769999742507935},{"id":"https://openalex.org/keywords/low-resource-language-translation","display_name":"low-resource translation","score":0.968999981880188},{"id":"https://openalex.org/keywords/back-translation","display_name":"back-translation","score":0.6990000009536743},{"id":"https://openalex.org/keywords/pivot-language","display_name":"pivot language","score":0.5049999952316284},{"id":"https://openalex.org/keywords/unsupervised-machine-translation","display_name":"unsupervised machine translation","score":0.9269999861717224},{"id":"https://openalex.org/keywords/monolingual-data","display_name":"monolingual data","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031445741653442},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7649298310279846},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.719748318195343},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6737101078033447},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6203885078430176},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.5945783853530884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5456016063690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351183414459229},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0903761088848114},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":3,"locations":[{"id":"doi:10.18653/v1/p19-1579","doi":"https://doi.org/10.18653/v1/p19-1579","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1579","pdf_url":"https://www.aclweb.org/anthology/P19-1579.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:1906.03785","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.03785","pdf_url":"https://arxiv.org/pdf/1906.03785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1906.03785","doi":"https://doi.org/10.48550/arxiv.1906.03785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.03785","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1579","doi":"https://doi.org/10.18653/v1/p19-1579","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1579","pdf_url":"https://www.aclweb.org/anthology/P19-1579.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2701169613","display_name":"Discovering and Demonstrating Linguistic Features for Language Documentation","funder_award_id":"1761548","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951476960.pdf","grobid_xml":"https://content.openalex.org/works/W2951476960.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W645927007","https://openalex.org/W2057069782","https://openalex.org/W2126725946","https://openalex.org/W2170204377","https://openalex.org/W2251566419","https://openalex.org/W2294774419","https://openalex.org/W2337363174","https://openalex.org/W2550821151","https://openalex.org/W2574872930","https://openalex.org/W2626778328","https://openalex.org/W2739978843","https://openalex.org/W2744813330","https://openalex.org/W2752630748","https://openalex.org/W2756566411","https://openalex.org/W2760424551","https://openalex.org/W2762484717","https://openalex.org/W2765961751","https://openalex.org/W2766182427","https://openalex.org/W2776822439","https://openalex.org/W2798994361","https://openalex.org/W2887920589","https://openalex.org/W2888173624","https://openalex.org/W2889191148","https://openalex.org/W2897058237","https://openalex.org/W2898799786","https://openalex.org/W2912095972","https://openalex.org/W2913659301","https://openalex.org/W2919290281","https://openalex.org/W2950733326","https://openalex.org/W2963206679","https://openalex.org/W2963216553","https://openalex.org/W2963331137","https://openalex.org/W2963413917","https://openalex.org/W2963506925","https://openalex.org/W2963602293","https://openalex.org/W2963993537","https://openalex.org/W2964085268","https://openalex.org/W3019421297","https://openalex.org/W4244167344","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2883671469","https://openalex.org/W2359639049","https://openalex.org/W2400846488"],"abstract_inverted_index":{"Translation":[0],"to":[1,32,73,77,85,140,142,147],"or":[2],"from":[3],"low-resource":[4,47,123,129],"languages":[5],"(LRLs)":[6],"poses":[7],"challenges":[8],"for":[9,43],"machine":[10,48,117],"translation":[11,49,118,136],"in":[12,46],"terms":[13],"of":[14,23,82,92],"both":[15],"adequacy":[16],"and":[17],"fluency.Data":[18],"augmentation":[19,45,133],"utilizing":[20],"large":[21],"amounts":[22],"monolingual":[24,55],"data":[25,44,76,90,132],"is":[26],"regarded":[27],"as":[28],"an":[29,103],"effective":[30],"way":[31],"alleviate":[33],"these":[34,110],"problems.In":[35],"this":[36],"paper,":[37],"we":[38,66,95,107],"propose":[39],"a":[40,61,69,114],"general":[41],"framework":[42],"that":[50,126],"not":[51],"only":[52],"uses":[53],"target-side":[54],"data,":[56],"but":[57],"also":[58],"pivots":[59],"through":[60,102],"related":[62],"highresource":[63],"language":[64],"(HRL).Specifically,":[65],"experiment":[67],"with":[68],"two-step":[70],"pivoting":[71],"method":[72],"convert":[74],"high-resource":[75],"the":[78,88,93],"LRL,":[79],"making":[80],"use":[81],"available":[83],"resources":[84],"better":[86],"approximate":[87],"true":[89],"distribution":[91],"LRL.First,":[94],"inject":[96],"LRL":[97],"words":[98],"into":[99],"HRL":[100],"sentences":[101,112],"induced":[104],"bilingual":[105],"dictionary.Second,":[106],"further":[108],"edit":[109],"modified":[111,115],"using":[113],"unsupervised":[116],"framework.Extensive":[119],"experiments":[120],"on":[121],"four":[122],"datasets":[124],"show":[125],"under":[127],"extreme":[128],"settings,":[130],"our":[131],"techniques":[134],"improve":[135],"quality":[137],"by":[138],"up":[139],"1.5":[141],"8":[143],"BLEU":[144],"points":[145],"compared":[146],"supervised":[148],"back-translation":[149],"baselines.1":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-18T09:31:52.927876","created_date":"2025-10-10T00:00:00"}