{"id":"https://openalex.org/W2970876710","doi":"https://doi.org/10.18653/v1/w19-5327","title":"Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring","display_name":"Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970876710","doi":"https://doi.org/10.18653/v1/w19-5327","mag":"2970876710"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5327","pdf_url":"https://www.aclweb.org/anthology/W19-5327.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 Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5327.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100623107","display_name":"Zihan Liu","orcid":"https://orcid.org/0000-0002-9692-4245"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zihan Liu","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378208","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0002-0271-044X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yan Xu","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085516032","display_name":"Genta Indra Winata","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Genta Indra Winata","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065856469"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.6802,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88409486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"282"},"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":0.9998999834060669,"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":0.9889000058174133,"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":0.8971414566040039},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8803781270980835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6826989650726318},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6823292374610901},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6684492230415344},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6492094993591309},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5670675039291382},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5045162439346313},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.5005486011505127},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4412095248699188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8971414566040039},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8803781270980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6826989650726318},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6823292374610901},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6684492230415344},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6492094993591309},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5670675039291382},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5045162439346313},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.5005486011505127},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4412095248699188},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w19-5327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5327","pdf_url":"https://www.aclweb.org/anthology/W19-5327.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 Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-101948","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2019&rft.spage=275&rft.aulast=Liu&rft.aufirst=&rft.atitle=Incorporating%20Word%20and%20Subword%20Units%20in%20Unsupervised%20Machine%20Translation%20Using%20Language%20Model%20Rescoring&rft.title=Proceedings%20of%20the%20Fourth%20Conference%20on%20Machine%20Translation","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-101948","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-101948","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5327","pdf_url":"https://www.aclweb.org/anthology/W19-5327.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 Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970876710.pdf","grobid_xml":"https://content.openalex.org/works/W2970876710.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2109000768","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2134800885","https://openalex.org/W2146574666","https://openalex.org/W2493916176","https://openalex.org/W2595715041","https://openalex.org/W2613904329","https://openalex.org/W2741602058","https://openalex.org/W2792376130","https://openalex.org/W2798931235","https://openalex.org/W2803214681","https://openalex.org/W2890007195","https://openalex.org/W2914120296","https://openalex.org/W2932618389","https://openalex.org/W2954447110","https://openalex.org/W2955866955","https://openalex.org/W2962677207","https://openalex.org/W2962784628","https://openalex.org/W2962824887","https://openalex.org/W2962832505","https://openalex.org/W2963118869","https://openalex.org/W2963216553","https://openalex.org/W2963403868","https://openalex.org/W2963418779","https://openalex.org/W2963602293","https://openalex.org/W2963684088","https://openalex.org/W2963993537","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W4297747548","https://openalex.org/W4298393544","https://openalex.org/W4299579390","https://openalex.org/W4299838440","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1485297680","https://openalex.org/W2782410293","https://openalex.org/W305958151","https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"CAiRE's":[3],"submission":[4],"to":[5,19,35,53,97,116],"the":[6,12,55,80,93,99,118],"unsupervised":[7],"machine":[8,26,39],"translation":[9,27,40,100],"track":[10],"of":[11,59,84,109,120],"WMT'19":[13],"news":[14],"shared":[15],"task":[16],"from":[17],"German":[18,68],"Czech.":[20],"We":[21,51],"leverage":[22],"a":[23,31,86,107],"phrase-based":[24],"statistical":[25],"(PBSMT)":[28],"model":[29,34,96],"and":[30,42,69,72,82,111],"pre-trained":[32,94],"language":[33,95],"combine":[36],"word-level":[37],"neural":[38],"(NMT)":[41],"subword-level":[43],"NMT":[44],"models":[45],"without":[46],"using":[47,76],"any":[48],"parallel":[49],"data.":[50],"propose":[52],"solve":[54],"morphological":[56],"richness":[57],"problem":[58],"languages":[60],"by":[61],"training":[62],"byte-pair":[63],"encoding":[64],"(BPE)":[65],"embeddings":[66],"for":[67],"Czech":[70],"separately,":[71],"they":[73],"are":[74,114],"aligned":[75],"MUSE":[77],"To":[78],"ensure":[79],"fluency":[81],"consistency":[83],"translations,":[85],"rescoring":[87],"mechanism":[88],"is":[89],"proposed":[90],"that":[91],"reuses":[92],"select":[98],"candidates":[101],"generated":[102],"through":[103],"beam":[104],"search.":[105],"Moreover,":[106],"series":[108],"pre-processing":[110],"post-processing":[112],"approaches":[113],"applied":[115],"improve":[117],"quality":[119],"final":[121],"translations.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}