{"id":"https://openalex.org/W2610850660","doi":"https://doi.org/10.18653/v1/p17-2090","title":"Data Augmentation for Low-Resource Neural Machine Translation","display_name":"Data Augmentation for Low-Resource Neural Machine Translation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2610850660","doi":"https://doi.org/10.18653/v1/p17-2090","mag":"2610850660"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2090","pdf_url":"https://www.aclweb.org/anthology/P17-2090.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 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2090.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Marzieh Fadaee","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marzieh Fadaee","raw_affiliation_strings":["Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arianna Bisazza","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arianna Bisazza","raw_affiliation_strings":["Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":null,"display_name":"Christof Monz","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christof Monz","raw_affiliation_strings":["Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam Science Park 904, 1098 XH Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":239,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"573"},"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":0.9986000061035156,"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/machine-translation","display_name":"Machine translation","score":0.8745999932289124},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.8068000078201294},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6812000274658203},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.541100025177002},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.44920000433921814},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35760000348091125}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8745999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.8068000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6876000165939331},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6812000274658203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6205999851226807},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.44920000433921814},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.34209999442100525},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2986258472","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation system","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/p17-2090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2090","pdf_url":"https://www.aclweb.org/anthology/P17-2090.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 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.00440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.00440","pdf_url":"https://arxiv.org/pdf/1705.00440","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/a4464493-3313-465f-bda4-ce8a99cbe79a","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/data-augmentation-for-lowresource-neural-machine-translation(a4464493-3313-465f-bda4-ce8a99cbe79a).html","pdf_url":"https://pure.uva.nl/ws/files/23199203/P17_2090.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fadaee, M, Bisazza, A & Monz, C 2017, Data Augmentation for Low-Resource Neural Machine Translation. in R Barzilay & M-Y Kan (eds), The 55th Annual Meeting of the Association for Computational Linguistics : proceedings of the Conference : July 30-August 4, 2017, Vancouver, Canada. vol. 2, Stroudsburg, PA, pp. 567-573, Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2090","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:rug:oai:pure.rug.nl:publications/7e06c56e-c6c1-4e19-83a1-68f438b29f94","is_oa":false,"landing_page_url":"https://www.rug.nl/research/portal/en/publications/data-augmentation-for-lowresource-neural-machine-translation(7e06c56e-c6c1-4e19-83a1-68f438b29f94).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 567 - 573","raw_type":"info:eu-repo/semantics/bookpart"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/a4464493-3313-465f-bda4-ce8a99cbe79a","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/data-augmentation-for-lowresource-neural-machine-translation(a4464493-3313-465f-bda4-ce8a99cbe79a).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 55th Annual Meeting of the Association for Computational Linguistics: proceedings of the Conference : July 30-August 4, 2017, Vancouver, Canada, 2, 567 - 573","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2090","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2090","pdf_url":"https://www.aclweb.org/anthology/P17-2090.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 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2354335809","display_name":"Connecting the Dots: Minimal Structure Modeling for Machine Translation","funder_award_id":"639.021.646","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2610850660.pdf","grobid_xml":"https://content.openalex.org/works/W2610850660.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2596164567"],"related_works":[],"abstract_inverted_index":{"The":[0],"quality":[1,73],"of":[2,13],"a":[3,39],"Neural":[4],"Machine":[5],"Translation":[6],"system":[7],"depends":[8],"substantially":[9],"on":[10,63],"the":[11,24,81],"availability":[12],"sizable":[14],"parallel":[15],"corpora.":[16],"For":[17],"low-resource":[18,65],"language":[19],"pairs":[20,52],"this":[21],"is":[22],"not":[23],"case,":[25],"resulting":[26],"in":[27,34,56],"poor":[28],"translation":[29,72],"quality.":[30],"Inspired":[31],"by":[32,48,74],"work":[33],"computer":[35],"vision,":[36],"we":[37],"propose":[38],"novel":[40],"data":[41],"augmentation":[42],"approach":[43],"that":[44,68],"targets":[45],"low-frequency":[46],"words":[47,55],"generating":[49],"new":[50],"sentence":[51],"containing":[53],"rare":[54],"new,":[57],"synthetically":[58],"created":[59],"contexts.":[60],"Experimental":[61],"results":[62],"simulated":[64],"settings":[66],"show":[67],"our":[69],"method":[70],"improves":[71],"up":[75,84],"to":[76,85],"2.9":[77],"BLEU":[78,87],"points":[79],"over":[80,88],"baseline":[82],"and":[83],"3.2":[86],"back-translation.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2017-05-12T00:00:00"}