{"id":"https://openalex.org/W2953063840","doi":"https://doi.org/10.18653/v1/w19-5435","title":"Low-Resource Corpus Filtering Using Multilingual Sentence Embeddings","display_name":"Low-Resource Corpus Filtering Using Multilingual Sentence Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2953063840","doi":"https://doi.org/10.18653/v1/w19-5435","mag":"2953063840"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5435","pdf_url":"https://aclanthology.org/W19-5435.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 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W19-5435.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053028004","display_name":"Vishrav Chaudhary","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Vishrav Chaudhary","raw_affiliation_strings":["Facebook AI Johns Hopkins University","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Johns Hopkins University","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071179460","display_name":"Yuqing Tang","orcid":"https://orcid.org/0000-0002-5919-1804"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yuqing Tang","raw_affiliation_strings":["Facebook AI Johns Hopkins University","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Johns Hopkins University","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113551755","display_name":"Francisco Guzm\u00e1n","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Francisco Guzm\u00e1n","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["Facebook AI Johns Hopkins University","Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook AI Johns Hopkins University","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112315093","display_name":"Philipp Koehn","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["Facebook AI Johns Hopkins University","Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Facebook AI Johns Hopkins University","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053028004"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.5783,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75307373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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":0.8404777646064758},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7431279420852661},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.676437497138977},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.6392626762390137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6139612197875977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562096893787384},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5163341760635376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5146247148513794},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4914432764053345},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4524582028388977},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4205642640590668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37916263937950134},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2712215483188629},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23160335421562195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404777646064758},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7431279420852661},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.676437497138977},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.6392626762390137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6139612197875977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562096893787384},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5163341760635376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5146247148513794},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4914432764053345},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4524582028388977},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4205642640590668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37916263937950134},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2712215483188629},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23160335421562195},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5435","pdf_url":"https://aclanthology.org/W19-5435.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 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.08885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08885","pdf_url":"https://arxiv.org/pdf/1906.08885","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1906.08885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.08885","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2953063840","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5435","pdf_url":"https://aclanthology.org/W19-5435.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 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953063840.pdf","grobid_xml":"https://content.openalex.org/works/W2953063840.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2050871273","https://openalex.org/W2124807415","https://openalex.org/W2141440284","https://openalex.org/W2773493195","https://openalex.org/W2798389157","https://openalex.org/W2899337869","https://openalex.org/W2902009742","https://openalex.org/W2902918014","https://openalex.org/W2903035303","https://openalex.org/W2905749056","https://openalex.org/W2913659301","https://openalex.org/W2933138175","https://openalex.org/W2962824887","https://openalex.org/W2963206679","https://openalex.org/W2963281280","https://openalex.org/W2963532001","https://openalex.org/W2963919854","https://openalex.org/W2970858854"],"related_works":["https://openalex.org/W2970686691","https://openalex.org/W2962735107","https://openalex.org/W3155542537","https://openalex.org/W2949375376","https://openalex.org/W2970117938","https://openalex.org/W2798389157","https://openalex.org/W3119453866","https://openalex.org/W3101789736","https://openalex.org/W2325518403","https://openalex.org/W2965538726","https://openalex.org/W3100096019","https://openalex.org/W2793761138","https://openalex.org/W3118643801","https://openalex.org/W3196406106","https://openalex.org/W3186927693","https://openalex.org/W2251693562","https://openalex.org/W2518455057","https://openalex.org/W3021414374","https://openalex.org/W2963206679","https://openalex.org/W2951184134"],"abstract_inverted_index":{"In":[0],"this":[1,127],"paper,":[2],"we":[3,79],"describe":[4],"our":[5,65,123],"submission":[6,92],"to":[7,38,49,67,117],"the":[8,22,46,53,94,100,118],"WMT19":[9],"low-resource":[10],"parallel":[11,36,55],"corpus":[12,37],"filtering":[13],"shared":[14],"task.":[15],"Our":[16,91],"main":[17],"approach":[18,66],"is":[19,129],"based":[20],"on":[21,34],"LASER":[23,74],"toolkit":[24],"(Language-Agnostic":[25],"SEntence":[26],"Representations),":[27],"which":[28],"uses":[29],"an":[30,81],"encoder-decoder":[31],"architecture":[32],"trained":[33],"a":[35,60,107],"obtain":[39,88],"multilingual":[40],"sentence":[41],"representations.":[42],"We":[43,63],"then":[44],"use":[45],"representations":[47],"directly":[48],"score":[50],"and":[51,71,87,102,111,133],"filter":[52],"noisy":[54],"sentences":[56],"without":[57],"additionally":[58],"training":[59],"scoring":[61,85],"function.":[62],"contrast":[64],"other":[68],"promising":[69,130],"methods":[70,86],"show":[72,125],"that":[73,126],"yields":[75],"strong":[76],"results.":[77],"Finally,":[78],"produce":[80],"ensemble":[82],"of":[83,109],"different":[84],"additional":[89],"gains.":[90],"achieved":[93],"best":[95,120],"overall":[96],"performance":[97],"for":[98,131],"both":[99],"Nepali-English":[101],"Sinhala-English":[103],"1M":[104],"tasks":[105],"by":[106],"margin":[108],"1.3":[110],"1.4":[112],"BLEU":[113],"respectively,":[114],"as":[115],"compared":[116],"second":[119],"systems.":[121],"Moreover,":[122],"experiments":[124],"technique":[128],"low":[132],"even":[134],"no-resource":[135],"scenarios.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}