{"id":"https://openalex.org/W2949756005","doi":"https://doi.org/10.18653/v1/p19-1581","title":"Better OOV Translation with Bilingual Terminology Mining","display_name":"Better OOV Translation with Bilingual Terminology Mining","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949756005","doi":"https://doi.org/10.18653/v1/p19-1581","mag":"2949756005"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1581","pdf_url":"https://www.aclweb.org/anthology/P19-1581.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1581.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051437051","display_name":"Matthias Huck","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Huck","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090950630","display_name":"Viktor Hangya","orcid":"https://orcid.org/0000-0002-5144-3069"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viktor Hangya","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061754269","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-1924-0015"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051437051"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":1.7342,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88621038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5809","last_page":"5815"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.8573163747787476},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7520363926887512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.711000919342041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511456370353699},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5902393460273743},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5642785429954529},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5434285998344421},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47189363837242126},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4637923836708069},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.4458768367767334},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.44307276606559753},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.39833834767341614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35312122106552124},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11558970808982849},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1118057370185852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8573163747787476},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7520363926887512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.711000919342041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511456370353699},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5902393460273743},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5642785429954529},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5434285998344421},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47189363837242126},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4637923836708069},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.4458768367767334},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.44307276606559753},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.39833834767341614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35312122106552124},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11558970808982849},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1118057370185852},{"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},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1581","pdf_url":"https://www.aclweb.org/anthology/P19-1581.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/p19-1581","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1581","pdf_url":"https://www.aclweb.org/anthology/P19-1581.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5399556803","display_name":null,"funder_award_id":"This project has received funding from the Europea","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6199968644","display_name":"Domain Adaptation for Statistical Machine Translation","funder_award_id":"640550","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949756005.pdf","grobid_xml":"https://content.openalex.org/works/W2949756005.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2118434577","https://openalex.org/W2124807415","https://openalex.org/W2126725946","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2251728420","https://openalex.org/W2294774419","https://openalex.org/W2493916176","https://openalex.org/W2507756961","https://openalex.org/W2594229957","https://openalex.org/W2595715041","https://openalex.org/W2757041753","https://openalex.org/W2757592053","https://openalex.org/W2758010889","https://openalex.org/W2798838126","https://openalex.org/W2799245424","https://openalex.org/W2804625779","https://openalex.org/W2811435848","https://openalex.org/W2902363747","https://openalex.org/W2962714778","https://openalex.org/W2962784628","https://openalex.org/W2962796826","https://openalex.org/W2962944953","https://openalex.org/W2963047628","https://openalex.org/W2963118869","https://openalex.org/W2963216553","https://openalex.org/W2963352809","https://openalex.org/W2963443683","https://openalex.org/W2964266061","https://openalex.org/W2964308564","https://openalex.org/W3104696873","https://openalex.org/W4299579390"],"related_works":["https://openalex.org/W193726211","https://openalex.org/W2134352815","https://openalex.org/W2570968448","https://openalex.org/W626175318","https://openalex.org/W2610387714","https://openalex.org/W2167761917","https://openalex.org/W3198193297","https://openalex.org/W2578428189","https://openalex.org/W2542068976","https://openalex.org/W2251488256"],"abstract_inverted_index":{"Unseen":[0],"words,":[1],"also":[2],"called":[3],"out-of-vocabulary":[4],"words":[5,86],"(OOVs),":[6],"are":[7,26],"difficult":[8],"for":[9,45],"machine":[10,14],"translation.":[11],"In":[12,62,133],"neural":[13],"translation,":[15],"byte-pair":[16],"encoding":[17],"can":[18,129],"be":[19,51,108,130],"used":[20],"to":[21,50,107,121],"represent":[22],"OOVs,":[23],"but":[24],"they":[25],"still":[27],"often":[28],"incorrectly":[29],"translated.":[30],"We":[31,43,93,113],"improve":[32],"the":[33,48,68,82,97,102,109,125],"translation":[34,126],"of":[35,81,99,101,127],"OOVs":[36,46,128],"in":[37,47],"NMT":[38],"using":[39,56,117],"easy-to-obtain":[40],"monolingual":[41,150],"data.":[42,151],"look":[44],"text":[49],"translated":[52],"and":[53,143],"translate":[54],"them":[55],"simple-to-construct":[57],"bilingual":[58],"word":[59],"embeddings":[60],"(BWEs).":[61],"our":[63,123,134],"MT":[64],"experiments":[65,135],"we":[66,89,136],"take":[67],"5-best":[69],"candidates,":[70],"which":[71],"is":[72],"motivated":[73],"by":[74,116],"intrinsic":[75],"mining":[76],"experiments.":[77],"Using":[78],"all":[79],"five":[80,103],"proposed":[83,104],"target":[84],"language":[85],"as":[87],"queries":[88],"mine":[90,144],"target-language":[91,105],"sentences.":[92],"then":[94],"back-translate,":[95],"forcing":[96],"back-translation":[98],"each":[100],"OOV-translation-candidates":[106],"original":[110],"source-language":[111],"OOV.":[112],"show":[114],"that":[115],"this":[118],"synthetic":[119],"data":[120],"finetune":[122],"system":[124,139],"dramatically":[131],"improved.":[132],"use":[137],"a":[138],"trained":[140],"on":[141],"Europarl":[142],"sentences":[145],"containing":[146],"medical":[147],"terms":[148],"from":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}