{"id":"https://openalex.org/W2987582383","doi":"https://doi.org/10.26615/978-954-452-056-4_013","title":"Naive Regularizers for Low-Resource Neural Machine Translation","display_name":"Naive Regularizers for Low-Resource Neural Machine Translation","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2987582383","doi":"https://doi.org/10.26615/978-954-452-056-4_013","mag":"2987582383"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_013","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_013","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"1Language Technology Group, Universit\u00e4t Hamburg, Hamburg, Germany","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"1Language Technology Group, Universit\u00e4t Hamburg, Hamburg, Germany","raw_affiliation_strings":["Language Technology Group, Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051998921","display_name":"Meriem Beloucif","orcid":"https://orcid.org/0000-0002-4659-759X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE","DK"],"is_corresponding":false,"raw_author_name":"Meriem Beloucif","raw_affiliation_strings":["Language Technology Group, Universitt Hamburg, Hamburg, Germany","Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group, Universitt Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]},{"raw_affiliation_string":"Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022823158","display_name":"Ana Valeria Gonz\u00e1lez","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ana Valeria Gonzalez","raw_affiliation_strings":["Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005438563","display_name":"Marcel Bollmann","orcid":"https://orcid.org/0000-0003-2598-8150"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Marcel Bollmann","raw_affiliation_strings":["Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpt. of Computer Science, University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59810866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"111"},"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":0.9894000291824341,"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":0.754082441329956},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5886639952659607},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.49001064896583557},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47929897904396057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46273764967918396},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09082034230232239},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06259465217590332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754082441329956},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5886639952659607},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49001064896583557},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47929897904396057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46273764967918396},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09082034230232239},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06259465217590332},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26615/978-954-452-056-4_013","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_013","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3820c76c-23b4-4ab8-b672-ed494ca870e9","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/3820c76c-23b4-4ab8-b672-ed494ca870e9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Beloucif , M , Gonzalez , A V , Bollmann , M & S\u00f8gaard , A 2019 , Naive regularizers for low-resource neural machine translation . in G Angelova , R Mitkov , I Nikolova , I Temnikova & I Temnikova (eds) , International Conference on Recent Advances in Natural Language Processing in a Deep Learning World, RANLP 2019 - Proceedings . Incoma Ltd , pp. 102-111 , 12th International Conference on Recent Advances in Natural Language Processing, RANLP 2019 , Varna , Bulgaria , 02/09/2019 . https://doi.org/10.26615/978-954-452-056-4_013","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_013","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_013","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_013","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987582383.pdf","grobid_xml":"https://content.openalex.org/works/W2987582383.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W24102868","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2124727305","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2144600658","https://openalex.org/W2149327368","https://openalex.org/W2184135559","https://openalex.org/W2251668285","https://openalex.org/W2251743902","https://openalex.org/W2550821151","https://openalex.org/W2595715041","https://openalex.org/W2613904329","https://openalex.org/W2886288106","https://openalex.org/W2962784628","https://openalex.org/W2962863357","https://openalex.org/W2963247703","https://openalex.org/W2963324947","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2964335437","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Neural":[0],"machine":[1],"translation":[2,60,116],"models":[3],"have":[4],"little":[5],"inductive":[6],"bias,":[7],"which":[8],"can":[9],"be":[10],"a":[11,107,126],"disadvantage":[12],"in":[13,123],"low-resource":[14,64],"scenarios.":[15],"They":[16],"require":[17],"large":[18],"volumes":[19],"of":[20,90,110],"data":[21,28,75],"and":[22,43,94],"often":[23],"perform":[24],"poorly":[25],"when":[26],"limited":[27],"is":[29],"available.":[30],"We":[31,66],"show":[32],"that":[33,49],"using":[34,120],"naive":[35],"regularization":[36],"methods,":[37],"based":[38],"on":[39,112],"sentence":[40,81],"length,":[41],"punctuation":[42,124],"word":[44],"frequencies,":[45],"to":[46,79],"penalize":[47],"translations":[48],"are":[50],"very":[51],"different":[52],"from":[53],"the":[54,59,73,100,113],"input":[55],"sentences,":[56],"consistently":[57],"improves":[58],"quality":[61],"across":[62,98],"multiple":[63],"languages.":[65],"experiment":[67],"with":[68],"12":[69],"language":[70,101],"pairs,":[71],"varying":[72],"training":[74],"size":[76],"between":[77],"17k":[78],"230k":[80],"pairs.":[82,102],"Our":[83],"best":[84],"regularizer":[85],"achieves":[86],"an":[87],"average":[88],"increase":[89],"1.5":[91],"BLEU":[92,108],"score":[93,97,109],"1.0":[95],"TER":[96],"all":[99],"For":[103],"example,":[104],"we":[105],"achieve":[106],"26.70":[111],"IWSLT15":[114],"English-Vietnamese":[115],"task":[117],"simply":[118],"by":[119],"relative":[121],"differences":[122],"as":[125],"regularizer.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-11-22T00:00:00"}