{"id":"https://openalex.org/W2963661177","doi":null,"title":"Synthetic and Natural Noise Both Break Neural Machine Translation","display_name":"Synthetic and Natural Noise Both Break Neural Machine Translation","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2963661177","mag":"2963661177"},"language":"en","primary_location":{"id":"mag:2963661177","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=BJ8vJebC-","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":"https://orcid.org/0000-0002-6280-5045","observed_orcids":["https://orcid.org/0000-0002-6280-5045"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041302228","display_name":"Yonatan Bisk","orcid":"https://orcid.org/0000-0002-2111-9081","observed_orcids":["https://orcid.org/0000-0002-2111-9081"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Bisk","raw_affiliation_strings":["University of Washington, Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, United States","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.8391,"has_fulltext":false,"cited_by_count":299,"citation_normalized_percentile":{"value":0.99565351,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9473000168800354,"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":0.9473000168800354,"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":0.039799999445676804,"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":0.0071000000461936,"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/neural-machine-translation","display_name":"neural machine translation","score":0.9120000004768372},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7770000100135803},{"id":"https://openalex.org/keywords/noisy-text","display_name":"noisy text","score":0.4099999964237213},{"id":"https://openalex.org/keywords/synthetic-noise","display_name":"synthetic noise","score":0.6980000138282776},{"id":"https://openalex.org/keywords/robust-training","display_name":"robust training","score":0.5479999780654907},{"id":"https://openalex.org/keywords/model-brittleness","display_name":"model brittleness","score":0.7879999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811431884765625},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7683154940605164},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.730806827545166},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6326587796211243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154648661613464},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5494049787521362},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46493810415267944},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.45556119084358215},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43985965847969055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42252954840660095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4187943935394287},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09995698928833008},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2963661177","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=BJ8vJebC-","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2914056350","https://openalex.org/W6931689928","https://openalex.org/W2916835973","https://openalex.org/W2986712369","https://openalex.org/W3200229070","https://openalex.org/W2805411799","https://openalex.org/W3085926550","https://openalex.org/W2967576208","https://openalex.org/W3118509208","https://openalex.org/W3008216235"],"abstract_inverted_index":{"Character-based":[0],"neural":[1,93],"machine":[2],"translation":[3,18],"(NMT)":[4],"models":[5,40,52],"alleviate":[6],"out-of-vocabulary":[7],"issues,":[8],"learn":[9,99],"morphology,":[10],"and":[11,26,43,77],"move":[12],"us":[13],"closer":[14],"to":[15,54,70,97,102],"completely":[16],"end-to-end":[17],"systems.":[19],"Unfortunately,":[20],"they":[21],"are":[22],"also":[23],"very":[24],"brittle":[25],"easily":[27],"falter":[28],"when":[29],"presented":[30],"with":[31,41],"noisy":[32,58,81],"data.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"confront":[38],"NMT":[39],"synthetic":[42],"natural":[44],"sources":[45],"of":[46,105],"noise.":[47,106],"We":[48,66,83],"find":[49,84],"that":[50,60,85],"state-of-the-art":[51],"fail":[53],"translate":[55],"even":[56],"moderately":[57],"texts":[59],"humans":[61],"have":[62],"no":[63],"trouble":[64],"comprehending.":[65],"explore":[67],"two":[68],"approaches":[69],"increase":[71],"model":[72,87],"robustness:":[73],"structure-invariant":[74],"word":[75],"representations":[76,100],"robust":[78,101],"training":[79],"on":[80,89],"texts.":[82],"a":[86,90],"based":[88],"character":[91],"convolutional":[92],"network":[94],"is":[95],"able":[96],"simultaneously":[98],"multiple":[103],"kinds":[104]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":110},{"year":2020,"cited_by_count":81},{"year":2019,"cited_by_count":72},{"year":2018,"cited_by_count":28}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}