{"id":"https://openalex.org/W2805411799","doi":"https://doi.org/10.18653/v1/w18-2709","title":"On the Impact of Various Types of Noise on Neural Machine Translation","display_name":"On the Impact of Various Types of Noise on Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2805411799","doi":"https://doi.org/10.18653/v1/w18-2709","mag":"2805411799"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-2709","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2709","pdf_url":"https://www.aclweb.org/anthology/W18-2709.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 2nd Workshop on Neural Machine Translation and Generation","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-2709.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huda Khayrallah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Huda Khayrallah","raw_affiliation_strings":["Center for Language & Speech Processing Computer Science Department Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Center for Language & Speech Processing Computer Science Department Johns Hopkins University","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":null,"display_name":"Philipp Koehn","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["Center for Language & Speech Processing Computer Science Department Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Center for Language & Speech Processing Computer Science Department Johns Hopkins University","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210156583"],"apc_list":null,"apc_paid":null,"fwci":1.5231,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.86952451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"83"},"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":0.9994000196456909,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9710999727249146,"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/noise","display_name":"Noise (video)","score":0.7784000039100647},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6410999894142151},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6072999835014343},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.43220001459121704},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.38359999656677246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.382099986076355},{"id":"https://openalex.org/keywords/statistical-noise","display_name":"Statistical noise","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7784000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934999823570251},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770999789237976},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4221000075340271},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C128197687","wikidata":"https://www.wikidata.org/wiki/Q5477515","display_name":"Statistical noise","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3547999858856201},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C2984485829","wikidata":"https://www.wikidata.org/wiki/Q100766421","display_name":"Noise level","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.26910001039505005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w18-2709","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2709","pdf_url":"https://www.aclweb.org/anthology/W18-2709.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 2nd Workshop on Neural Machine Translation and Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.12282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.12282","pdf_url":"https://arxiv.org/pdf/1805.12282","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"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-2709","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-2709","pdf_url":"https://www.aclweb.org/anthology/W18-2709.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 2nd Workshop on Neural Machine Translation and Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3429874898","display_name":null,"funder_award_id":"LORELEI","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805411799.pdf","grobid_xml":"https://content.openalex.org/works/W2805411799.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2572136474"],"related_works":[],"abstract_inverted_index":{"We":[0,20,39],"examine":[1],"how":[2,29],"various":[3],"types":[4,23],"of":[5,15,24,58],"noise":[6,26,49,59],"in":[7,33],"the":[8,13,65],"parallel":[9],"training":[10],"data":[11],"impact":[12],"quality":[14],"neural":[16,34,42],"machine":[17,37],"translation":[18],"systems.":[19],"create":[21],"five":[22],"artificial":[25],"and":[27,35],"analyze":[28],"they":[30,60],"degrade":[31],"performance":[32],"statistical":[36,51],"translation.":[38],"find":[40],"that":[41],"models":[43],"are":[44],"generally":[45],"more":[46],"harmed":[47],"by":[48],"than":[50],"models.":[52],"For":[53],"one":[54],"especially":[55],"egregious":[56],"type":[57],"learn":[61],"to":[62],"just":[63],"copy":[64],"input":[66],"sentence.":[67]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2018-06-13T00:00:00"}