{"id":"https://openalex.org/W2891520362","doi":"https://doi.org/10.18653/v1/w18-6478","title":"Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora","display_name":"Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891520362","doi":"https://doi.org/10.18653/v1/w18-6478","mag":"2891520362"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6478","pdf_url":"https://www.aclweb.org/anthology/W18-6478.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6478.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065193578","display_name":"Marcin Junczys-Dowmunt","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Microsoft 1 Microsoft Way Redmond, WA 98121, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft 1 Microsoft Way Redmond, WA 98121, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065193578"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.79424984,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76948562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"888","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.7450221180915833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.590090811252594},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.506255567073822},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48216837644577026},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4755394458770752},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.47513797879219055},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.4671430289745331},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4659600853919983},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.45369982719421387},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4439478814601898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35730183124542236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392093777656555},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.29776400327682495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450221180915833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590090811252594},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.506255567073822},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48216837644577026},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4755394458770752},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.47513797879219055},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.4671430289745331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4659600853919983},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.45369982719421387},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4439478814601898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35730183124542236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392093777656555},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.29776400327682495},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-6478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6478","pdf_url":"https://www.aclweb.org/anthology/W18-6478.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.00197","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.00197","pdf_url":"https://arxiv.org/pdf/1809.00197","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":"mag:2891520362","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.00197.pdf","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":"doi:10.48550/arxiv.1809.00197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.00197","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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6478","pdf_url":"https://www.aclweb.org/anthology/W18-6478.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 Third Conference on Machine Translation: Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891520362.pdf","grobid_xml":"https://content.openalex.org/works/W2891520362.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1905522558","https://openalex.org/W2117278770","https://openalex.org/W2767899794","https://openalex.org/W2794365787","https://openalex.org/W2798389157","https://openalex.org/W2902918014","https://openalex.org/W2950359962","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963919854"],"related_works":["https://openalex.org/W2963281280","https://openalex.org/W3131802060","https://openalex.org/W2970155092","https://openalex.org/W2162583378","https://openalex.org/W2250890374","https://openalex.org/W2951985405","https://openalex.org/W1887786044","https://openalex.org/W2550969009","https://openalex.org/W2177717508","https://openalex.org/W2086846715","https://openalex.org/W1986468312","https://openalex.org/W2433238124","https://openalex.org/W2148922863","https://openalex.org/W1519512946","https://openalex.org/W3028222090","https://openalex.org/W2135919823","https://openalex.org/W2560567690","https://openalex.org/W2945405384","https://openalex.org/W3129146692","https://openalex.org/W2741442884"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,22],"introduce":[4],"dual":[5],"conditional":[6],"cross-entropy":[7,24,46],"filtering":[8,104],"for":[9],"noisy":[10,19],"parallel":[11,20,63,74,102],"data.":[12,35,64,87],"For":[13],"each":[14],"sentence":[15],"pair":[16],"of":[17,48,62,96,112,121],"the":[18,42,45,94,97,107,113],"corpus":[21,103],"compute":[23],"scores":[25,57,69,111],"according":[26,54],"to":[27,55],"two":[28],"inverse":[29],"translation":[30],"models":[31,71,82],"trained":[32,72,83],"on":[33,73,84,101],"clean":[34,85],"We":[36,65,88],"penalize":[37],"divergent":[38],"cross-entropies":[39],"and":[40,105],"weigh":[41],"penalty":[43],"by":[44],"average":[47],"both":[49],"models.":[50],"Sorting":[51],"or":[52],"thresholding":[53],"these":[56],"results":[58],"in":[59,93,118],"better":[60],"subsets":[61],"achieve":[66,106],"higher":[67],"BLEU":[68],"with":[70,81],"data":[75],"filtered":[76],"only":[77],"from":[78],"Paracrawl":[79],"than":[80],"WMT":[86],"further":[89],"evaluate":[90],"our":[91],"method":[92],"context":[95],"WMT2018":[98],"shared":[99,114],"task":[100],"overall":[108],"highest":[109],"ranking":[110],"task,":[115],"scoring":[116],"top":[117],"three":[119],"out":[120],"four":[122],"subtasks.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}