{"id":"https://openalex.org/W3093421262","doi":"https://doi.org/10.1162/tacl_a_00348","title":"Unsupervised Bitext Mining and Translation via Self-Trained Contextual Embeddings","display_name":"Unsupervised Bitext Mining and Translation via Self-Trained Contextual Embeddings","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3093421262","doi":"https://doi.org/10.1162/tacl_a_00348","mag":"3093421262"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00348","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00348","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00348/1923065/tacl_a_00348.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00348/1923065/tacl_a_00348.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073224570","display_name":"Phillip Keung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Phillip Keung","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037283647","display_name":"Juli\u00e1n Salazar","orcid":"https://orcid.org/0000-0003-0943-7594"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Salazar","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089283502","display_name":"Yichao Lu","orcid":"https://orcid.org/0009-0001-2005-1724"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yichao Lu","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"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"]},{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":["Allen Institute for AI","University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2685,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67120772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"8","issue":null,"first_page":"828","last_page":"841"},"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":0.9765999913215637,"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":0.8636425733566284},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.731789767742157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7102155089378357},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6809540390968323},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6146513223648071},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6089392900466919},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47089651226997375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33070820569992065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636425733566284},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.731789767742157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7102155089378357},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6809540390968323},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6146513223648071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6089392900466919},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47089651226997375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33070820569992065},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00348","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00348","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00348/1923065/tacl_a_00348.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.07761","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.07761","pdf_url":"https://arxiv.org/pdf/2010.07761","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"},{"id":"mag:3093421262","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.07761","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:0da8d7013fe3491f962eb5600cd44675","is_oa":false,"landing_page_url":"https://doaj.org/article/0da8d7013fe3491f962eb5600cd44675","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 8 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2010.07761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.07761","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00348","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00348","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00348/1923065/tacl_a_00348.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1636405317","https://openalex.org/W2047295649","https://openalex.org/W2101210369","https://openalex.org/W2143927888","https://openalex.org/W2593864460","https://openalex.org/W2742155240","https://openalex.org/W2798389157","https://openalex.org/W2885950361","https://openalex.org/W2886095922","https://openalex.org/W2886198413","https://openalex.org/W2891602716","https://openalex.org/W2892004290","https://openalex.org/W2902918014","https://openalex.org/W2905927205","https://openalex.org/W2944815030","https://openalex.org/W2949405462","https://openalex.org/W2950342398","https://openalex.org/W2960374072","https://openalex.org/W2962696263","https://openalex.org/W2962735107","https://openalex.org/W2962778428","https://openalex.org/W2963206679","https://openalex.org/W2963216553","https://openalex.org/W2963341956","https://openalex.org/W2963532001","https://openalex.org/W2964013027","https://openalex.org/W2964308564","https://openalex.org/W2970049541","https://openalex.org/W2970157301","https://openalex.org/W2970283086","https://openalex.org/W2971105085","https://openalex.org/W2973088264","https://openalex.org/W2979636403","https://openalex.org/W2983221611","https://openalex.org/W3008618223","https://openalex.org/W3034579764","https://openalex.org/W3104652516","https://openalex.org/W3204406378"],"related_works":["https://openalex.org/W3119378114","https://openalex.org/W3164405410","https://openalex.org/W3101672304","https://openalex.org/W2902949028","https://openalex.org/W3153073450","https://openalex.org/W3176344506","https://openalex.org/W3025490068","https://openalex.org/W3212833915","https://openalex.org/W2293259138","https://openalex.org/W2951522086","https://openalex.org/W3198803846","https://openalex.org/W2807342354","https://openalex.org/W3200079248","https://openalex.org/W3152712567","https://openalex.org/W3171803676","https://openalex.org/W3198013311","https://openalex.org/W2524025421","https://openalex.org/W3092468804","https://openalex.org/W2250398693","https://openalex.org/W2251113547"],"abstract_inverted_index":{"We":[0,16,36,69,136],"describe":[1],"an":[2,72,143],"unsupervised":[3,67,74,93,139],"method":[4],"to":[5,20,55,98],"create":[6,21],"pseudo-parallel":[7,85,122],"corpora":[8],"for":[9,27],"machine":[10],"translation":[11,94],"(MT)":[12],"from":[13,88],"unaligned":[14],"text.":[15],"use":[17],"multilingual":[18],"BERT":[19],"source":[22],"and":[23,30,52,105,109,150],"target":[24],"sentence":[25,43,124],"embeddings":[26],"nearest-neighbor":[28],"search":[29],"adapt":[31],"the":[32,46,89,102,111,117,132],"model":[33],"via":[34],"self-training.":[35],"validate":[37],"our":[38],"technique":[39],"by":[40,81,96],"extracting":[41],"parallel":[42],"pairs":[44],"on":[45,79,101,131],"BUCC":[47],"2017":[48],"bitext":[49,140],"mining":[50,141],"task":[51],"observe":[53],"up":[54,97],"a":[56,127],"24.5":[57],"point":[58],"increase":[59],"(absolute)":[60],"in":[61],"F":[62],"1":[63],"scores":[64],"over":[65],"previous":[66,112],"methods.":[68],"then":[70],"improve":[71],"XLM-based":[73],"neural":[75],"MT":[76,134,148],"system":[77],"pre-trained":[78,157],"Wikipedia":[80,123],"supplementing":[82],"it":[83],"with":[84,121,156],"text":[86],"mined":[87],"same":[90],"corpus,":[91],"boosting":[92],"performance":[95],"3.5":[99],"BLEU":[100,129],"WMT\u201914":[103],"French-English":[104],"WMT\u201916":[106],"German-English":[107],"tasks":[108],"outperforming":[110],"state-of-the-art.":[113],"Finally,":[114],"we":[115],"enrich":[116],"IWSLT\u201915":[118],"English-Vietnamese":[119],"corpus":[120],"pairs,":[125],"yielding":[126],"1.2":[128],"improvement":[130],"low-resource":[133],"task.":[135],"demonstrate":[137],"that":[138],"is":[142],"effective":[144],"way":[145],"of":[146],"augmenting":[147],"datasets":[149],"complements":[151],"existing":[152],"techniques":[153],"like":[154],"initializing":[155],"contextual":[158],"embeddings.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}