{"id":"https://openalex.org/W3119188361","doi":"https://doi.org/10.18653/v1/2020.wmt-1.109","title":"Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task","display_name":"Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3119188361","doi":"https://doi.org/10.18653/v1/2020.wmt-1.109","mag":"3119188361"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.109","pdf_url":"https://aclanthology.org/2020.wmt-1.109.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.109.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010037961","display_name":"Felicia Koerner","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felicia Koerner","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University","Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.2709,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66499617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"966","last_page":"971"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.6151549220085144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5646257996559143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575281977653503},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5273321866989136},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.48280155658721924},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47785183787345886},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45559361577033997},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4163750410079956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3635319471359253},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3483452796936035},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3192899227142334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151549220085144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5646257996559143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575281977653503},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5273321866989136},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.48280155658721924},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47785183787345886},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45559361577033997},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4163750410079956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3635319471359253},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3483452796936035},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3192899227142334},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.109","pdf_url":"https://aclanthology.org/2020.wmt-1.109.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"mag:3119188361","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.109.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.109","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.109","pdf_url":"https://aclanthology.org/2020.wmt-1.109.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 Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119188361.pdf","grobid_xml":"https://content.openalex.org/works/W3119188361.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2902918014","https://openalex.org/W2903035303","https://openalex.org/W2933138175","https://openalex.org/W2963281280","https://openalex.org/W2963506925","https://openalex.org/W2963919854","https://openalex.org/W2970686691","https://openalex.org/W3107826490"],"related_works":["https://openalex.org/W3118434027","https://openalex.org/W2917025446","https://openalex.org/W2127293685","https://openalex.org/W2917098612","https://openalex.org/W2395971734","https://openalex.org/W2464151748","https://openalex.org/W2003484529","https://openalex.org/W3120955312","https://openalex.org/W2807245740","https://openalex.org/W2463861136","https://openalex.org/W3119072192","https://openalex.org/W3034775979","https://openalex.org/W2982621400","https://openalex.org/W2963842834","https://openalex.org/W2100643971","https://openalex.org/W2759035416","https://openalex.org/W2073450104","https://openalex.org/W170072012","https://openalex.org/W2954635489","https://openalex.org/W212464659"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"submission":[4,36],"to":[5,46],"the":[6,57,63,88,95,108,113,117],"WMT20":[7],"Parallel":[8],"Corpus":[9],"Filtering":[10],"and":[11,23,28,66,72,92],"Alignment":[12],"for":[13,116,120],"Low-Resource":[14],"Conditions":[15],"Shared":[16],"Task.This":[17],"year's":[18],"corpora":[19],"are":[20],"noisy":[21,109],"Khmer-English":[22],"Pashto-English,":[24,40],"with":[25,81,103],"58.3":[26],"million":[27,30],"11.6":[29],"words":[31],"respectively":[32],"(English":[33],"token":[34],"count).Our":[35],"focuses":[37],"on":[38,42,87],"filtering":[39],"building":[41],"previously":[43],"successful":[44],"methods":[45],"produce":[47],"two":[48],"sets":[49],"of":[50,56,107],"scores:":[51],"LASER":[52,58,89],"LM,":[53],"a":[54,82,104],"combination":[55],"similarity":[59,90],"scores":[60,68,79],"provided":[61,96],"in":[62],"shared":[64],"task":[65],"perplexity":[67],"from":[69],"language":[70],"models,":[71],"DCCEF":[73],"DUP,":[74],"dual":[75,121],"conditional":[76,122],"cross":[77,123],"entropy":[78,124],"combined":[80],"duplication":[83],"penalty.We":[84],"improve":[85],"slightly":[86],"score":[91],"find":[93],"that":[94],"clean":[97],"data":[98,115],"can":[99],"successfully":[100],"be":[101],"supplemented":[102],"subsampled":[105],"set":[106],"data,":[110],"effectively":[111],"increasing":[112],"training":[114],"models":[118],"used":[119],"scoring.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2021-01-18T00:00:00"}