{"id":"https://openalex.org/W3119872155","doi":"https://doi.org/10.18653/v1/2020.wmt-1.78","title":"Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment","display_name":"Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3119872155","doi":"https://doi.org/10.18653/v1/2020.wmt-1.78","mag":"3119872155"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.78","pdf_url":"https://aclanthology.org/2020.wmt-1.78.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.78.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053028004","display_name":"Vishrav Chaudhary","orcid":null},"institutions":[{"id":"https://openalex.org/I119664326","display_name":"University of Wolverhampton","ror":"https://ror.org/01k2y1055","country_code":"GB","type":"education","lineage":["https://openalex.org/I119664326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vishrav Chaudhary","raw_affiliation_strings":["University of Wolverhampton, Wolverhampton, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wolverhampton, Wolverhampton, United Kingdom","institution_ids":["https://openalex.org/I119664326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035119055","display_name":"Ahmed El-Kishky","orcid":"https://orcid.org/0000-0003-0121-7781"},"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":"Ahmed El-Kishky","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075834790","display_name":"Naman Goyal","orcid":"https://orcid.org/0000-0002-7565-4303"},"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":"Naman Goyal","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072019513","display_name":"Peng\u2010Jen Chen","orcid":"https://orcid.org/0000-0001-5400-905X"},"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":"Peng-Jen Chen","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","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":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"726","last_page":"742"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9866999983787537,"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":0.8252162933349609},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7394646406173706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7256186008453369},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7170668244361877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6929155588150024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6418153047561646},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5019612312316895},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4776843190193176},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44384336471557617},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3987971544265747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3943478763103485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252162933349609},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7394646406173706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7256186008453369},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7170668244361877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6929155588150024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6418153047561646},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5019612312316895},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4776843190193176},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44384336471557617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3987971544265747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3943478763103485},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.78","pdf_url":"https://aclanthology.org/2020.wmt-1.78.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:3119872155","is_oa":false,"landing_page_url":"https://aclanthology.org/2020.wmt-1.78/","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-1.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.78","pdf_url":"https://aclanthology.org/2020.wmt-1.78.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":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3119872155.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W37508832","https://openalex.org/W630532510","https://openalex.org/W1489181569","https://openalex.org/W1819903106","https://openalex.org/W1905522558","https://openalex.org/W2129734311","https://openalex.org/W2145080939","https://openalex.org/W2148334774","https://openalex.org/W2168929382","https://openalex.org/W2170632340","https://openalex.org/W2170716095","https://openalex.org/W2185142058","https://openalex.org/W2250929565","https://openalex.org/W2496235729","https://openalex.org/W2508809683","https://openalex.org/W2513768144","https://openalex.org/W2552839021","https://openalex.org/W2572474373","https://openalex.org/W2741900445","https://openalex.org/W2760656271","https://openalex.org/W2773493195","https://openalex.org/W2787646045","https://openalex.org/W2798389157","https://openalex.org/W2902918014","https://openalex.org/W2919188216","https://openalex.org/W2919290281","https://openalex.org/W2933138175","https://openalex.org/W2962890089","https://openalex.org/W2963206679","https://openalex.org/W2963281280","https://openalex.org/W2963366389","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2963532001","https://openalex.org/W2963661177","https://openalex.org/W2963919854","https://openalex.org/W2964308564","https://openalex.org/W2970559709","https://openalex.org/W2970686691","https://openalex.org/W2970858854","https://openalex.org/W2970986500","https://openalex.org/W2986148666","https://openalex.org/W3003748523","https://openalex.org/W3022297718","https://openalex.org/W3035016936","https://openalex.org/W3035390927","https://openalex.org/W3093871477","https://openalex.org/W3105425516","https://openalex.org/W3107826490","https://openalex.org/W3118265739","https://openalex.org/W3118434027","https://openalex.org/W3119188361","https://openalex.org/W3119453866","https://openalex.org/W3119590346","https://openalex.org/W3120253636","https://openalex.org/W3120697923","https://openalex.org/W3201817155"],"related_works":["https://openalex.org/W2970858854","https://openalex.org/W2963403868","https://openalex.org/W2101105183","https://openalex.org/W2902918014","https://openalex.org/W2963919854","https://openalex.org/W2963250244","https://openalex.org/W2903182367","https://openalex.org/W3107826490","https://openalex.org/W2962784628","https://openalex.org/W2902969394","https://openalex.org/W2903151286","https://openalex.org/W2970185230","https://openalex.org/W2952926668","https://openalex.org/W2902127193","https://openalex.org/W2508803094","https://openalex.org/W2903035303","https://openalex.org/W2970463863","https://openalex.org/W3096972693","https://openalex.org/W2963088657","https://openalex.org/W3120253636"],"abstract_inverted_index":{"Following":[0],"two":[1],"preceding":[2],"WMT":[3],"Shared":[4],"Task":[5],"on":[6],"Parallel":[7],"Corpus":[8],"Filtering":[9],"(Koehn":[10],"et":[11],"al.,":[12],"2018,":[13],"2019),":[14],"we":[15],"posed":[16],"again":[17],"the":[18,34,37,41,54,57,68],"challenge":[19,69],"of":[20,29,39,61,70],"assigning":[21],"sentence-level":[22],"quality":[23],"scores":[24],"for":[25],"very":[26],"noisy":[27],"corpora":[28],"sentence":[30,71],"pairs":[31],"crawled":[32],"from":[33,73],"web,":[35],"with":[36],"goal":[38],"sub-selecting":[40],"highest-quality":[42],"data":[43],"to":[44,47],"be":[45],"used":[46],"train":[48],"ma-chine":[49],"translation":[50],"systems.":[51],"This":[52],"year,":[53],"task":[55],"tackled":[56],"low":[58],"resource":[59],"condition":[60],"Pashto\u2013English":[62],"and":[63,65],"Khmer\u2013English":[64],"also":[66],"included":[67],"alignment":[72],"document":[74],"pairs.":[75]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-01-18T00:00:00"}