{"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","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":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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1579.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003465314","display_name":"Mengzhou Xia","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"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},"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"],"raw_orcid":null,"affiliations":[{"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"},"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"],"raw_orcid":null,"affiliations":[{"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"},"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"],"raw_orcid":null,"affiliations":[{"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":null,"has_fulltext":true,"cited_by_count":110,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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":0.9997000098228455,"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":0.9898999929428101,"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":0.8031445741653442},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.7649298310279846},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.719748318195343},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6737101078033447},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6203885078430176},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.5945783853530884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5456016063690186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351183414459229},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0903761088848114}],"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":1,"locations":[{"id":"doi: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":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/p19-1579","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":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":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951476960.pdf","grobid_xml":"https://content.openalex.org/works/W2951476960.grobid-xml"},"referenced_works_count":45,"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/W2550821151","https://openalex.org/W2610245951","https://openalex.org/W2739978843","https://openalex.org/W2744813330","https://openalex.org/W2752630748","https://openalex.org/W2756566411","https://openalex.org/W2760424551","https://openalex.org/W2776822439","https://openalex.org/W2798931235","https://openalex.org/W2887920589","https://openalex.org/W2888173624","https://openalex.org/W2889191148","https://openalex.org/W2897058237","https://openalex.org/W2898799786","https://openalex.org/W2899490399","https://openalex.org/W2912095972","https://openalex.org/W2913659301","https://openalex.org/W2919290281","https://openalex.org/W2950733326","https://openalex.org/W2962824887","https://openalex.org/W2963088995","https://openalex.org/W2963212250","https://openalex.org/W2963216553","https://openalex.org/W2963331137","https://openalex.org/W2963403868","https://openalex.org/W2963413917","https://openalex.org/W2963506925","https://openalex.org/W2963602293","https://openalex.org/W2963617771","https://openalex.org/W2963633299","https://openalex.org/W2963831310","https://openalex.org/W2963993537","https://openalex.org/W2964085268","https://openalex.org/W3019421297","https://openalex.org/W4244167344","https://openalex.org/W4288601832","https://openalex.org/W4298393544","https://openalex.org/W4299579390","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":[1,33,76,80,88,146,148,153],"or":[2],"from":[3],"low-resource":[4,49,129,135],"languages":[5],"(LRLs)":[6],"poses":[7],"challenges":[8],"for":[9,45],"machine":[10,50,122],"translation":[11,51,123,142],"in":[12,48],"terms":[13],"of":[14,24,85,95],"both":[15],"adequacy":[16],"and":[17],"fluency.":[18],"Data":[19],"augmentation":[20,47,139],"utilizing":[21],"large":[22],"amounts":[23],"monolingual":[25,57],"data":[26,46,79,93,138],"is":[27],"regarded":[28],"as":[29],"an":[30,107],"effective":[31],"way":[32],"alleviate":[34],"these":[35,115],"problems.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,69,99,112],"propose":[41],"a":[42,63,72,119],"general":[43],"framework":[44],"that":[52,132],"not":[53],"only":[54],"uses":[55],"target-side":[56],"data,":[58],"but":[59],"also":[60],"pivots":[61],"through":[62,106],"related":[64],"highresource":[65],"language":[66],"(HRL).":[67],"Specifically,":[68],"experiment":[70],"with":[71],"two-step":[73],"pivoting":[74],"method":[75],"convert":[77],"high-resource":[78],"the":[81,91,96],"LRL,":[82],"making":[83],"use":[84],"available":[86],"resources":[87],"better":[89],"approximate":[90],"true":[92],"distribution":[94],"LRL.":[97],"First,":[98],"inject":[100],"LRL":[101],"words":[102],"into":[103],"HRL":[104],"sentences":[105,117],"induced":[108],"bilingual":[109],"dictionary.":[110],"Second,":[111],"further":[113],"edit":[114],"modified":[116,120],"using":[118],"unsupervised":[121],"framework.":[124],"Extensive":[125],"experiments":[126],"on":[127],"four":[128],"datasets":[130],"show":[131],"under":[133],"extreme":[134],"settings,":[136],"our":[137],"techniques":[140],"improve":[141],"quality":[143],"by":[144],"up":[145],"1.5":[147],"8":[149],"BLEU":[150],"points":[151],"compared":[152],"supervised":[154],"back-translation":[155],"baselines.":[156],"1":[157]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}