{"id":"https://openalex.org/W2902918014","doi":"https://doi.org/10.18653/v1/w18-6453","title":"Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering","display_name":"Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902918014","doi":"https://doi.org/10.18653/v1/w18-6453","mag":"2902918014"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6453","pdf_url":"https://www.aclweb.org/anthology/W18-6453.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6453.pdf","any_repository_has_fulltext":true},"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":["Computer Science Department Johns Hopkins University Baltimore, Maryland, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Johns Hopkins University Baltimore, Maryland, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080544452","display_name":"Huda Khayrallah","orcid":"https://orcid.org/0000-0002-2920-6745"},"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":"Huda Khayrallah","raw_affiliation_strings":["Computer Science Department Johns Hopkins University Baltimore, Maryland, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Johns Hopkins University Baltimore, Maryland, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I1320481043","display_name":"European Union","ror":"https://ror.org/019w4f821","country_code":"BE","type":"government","lineage":["https://openalex.org/I1320481043"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["BE","GB"],"is_corresponding":true,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["School of Informatics University of Edinburgh Edinburgh, Scotland, European Union"],"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh Edinburgh, Scotland, European Union","institution_ids":["https://openalex.org/I1320481043","https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001715786","display_name":"Mikel L. Forcada","orcid":"https://orcid.org/0000-0003-0843-6442"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]},{"id":"https://openalex.org/I4210095713","display_name":"Departament de Salut","ror":"https://ror.org/00nyrjc53","country_code":"ES","type":"funder","lineage":["https://openalex.org/I157913058","https://openalex.org/I4210095713"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mikel L. Forcada","raw_affiliation_strings":["Departament de Llenguatges i Sistemes Informtics Universitat d'Alacant 03690 St. Vicent del Raspeig, Spain","Departament de Llenguatges i Sistemes Inform\u00e0tics Universitat d'Alacant 03690 St. Vicent del Raspeig, Spain"],"affiliations":[{"raw_affiliation_string":"Departament de Llenguatges i Sistemes Informtics Universitat d'Alacant 03690 St. Vicent del Raspeig, Spain","institution_ids":["https://openalex.org/I4210095713"]},{"raw_affiliation_string":"Departament de Llenguatges i Sistemes Inform\u00e0tics Universitat d'Alacant 03690 St. Vicent del Raspeig, Spain","institution_ids":["https://openalex.org/I130194489"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070589644"],"corresponding_institution_ids":["https://openalex.org/I1320481043","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":14.215,"has_fulltext":true,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98996661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"726","last_page":"739"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9937000274658203,"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/task","display_name":"Task (project management)","score":0.8370135426521301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906899452209473},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7840197682380676},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6952757835388184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6384375691413879},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.605129063129425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5498167276382446},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42762359976768494},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4089266359806061},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3485734462738037},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3232411742210388},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0599077045917511}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8370135426521301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906899452209473},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7840197682380676},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6952757835388184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6384375691413879},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.605129063129425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5498167276382446},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42762359976768494},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4089266359806061},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3485734462738037},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3232411742210388},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0599077045917511},{"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/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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w18-6453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6453","pdf_url":"https://www.aclweb.org/anthology/W18-6453.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:pure.ed.ac.uk:publications/b8f27cfa-5fb9-4a07-be57-037694cf0ab9","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/b8f27cfa-5fb9-4a07-be57-037694cf0ab9","pdf_url":"https://www.research.ed.ac.uk/en/publications/b8f27cfa-5fb9-4a07-be57-037694cf0ab9","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b8f27cfa-5fb9-4a07-be57-037694cf0ab9","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/b8f27cfa-5fb9-4a07-be57-037694cf0ab9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Koehn, P, Khayrallah, H, Heafield, K & Forcada, M L 2018, Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering. in Proceedings of the Third Conference on Machine Translation: Shared Task Papers. Belgium, Brussels, pp. 726-739, EMNLP 2018 Third Conference on Machine Translation (WMT18), Brussels, Belgium, 31/10/18. https://doi.org/10.18653/v1/W18-64080","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6453","pdf_url":"https://www.aclweb.org/anthology/W18-6453.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":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902918014.pdf","grobid_xml":"https://content.openalex.org/works/W2902918014.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W37508832","https://openalex.org/W338621447","https://openalex.org/W630532510","https://openalex.org/W1905522558","https://openalex.org/W2124807415","https://openalex.org/W2129734311","https://openalex.org/W2145080939","https://openalex.org/W2170632340","https://openalex.org/W2185142058","https://openalex.org/W2250929565","https://openalex.org/W2460354904","https://openalex.org/W2496235729","https://openalex.org/W2508809683","https://openalex.org/W2572474373","https://openalex.org/W2595715041","https://openalex.org/W2741787148","https://openalex.org/W2741900445","https://openalex.org/W2767899794","https://openalex.org/W2773493195","https://openalex.org/W2795467683","https://openalex.org/W2891520362","https://openalex.org/W2891625970","https://openalex.org/W2902009742","https://openalex.org/W2902127193","https://openalex.org/W2902319873","https://openalex.org/W2902643185","https://openalex.org/W2902831278","https://openalex.org/W2902867443","https://openalex.org/W2902949028","https://openalex.org/W2902969394","https://openalex.org/W2903035303","https://openalex.org/W2903061071","https://openalex.org/W2903151286","https://openalex.org/W2903182367","https://openalex.org/W2903249572","https://openalex.org/W2903253760","https://openalex.org/W2903297715","https://openalex.org/W2963281280","https://openalex.org/W2963366389","https://openalex.org/W2963661177","https://openalex.org/W2963919854","https://openalex.org/W2964343359","https://openalex.org/W3119453866","https://openalex.org/W3201817155","https://openalex.org/W6601523051","https://openalex.org/W6681116826","https://openalex.org/W6723821839","https://openalex.org/W6731744468","https://openalex.org/W6756128663","https://openalex.org/W6756657654","https://openalex.org/W6756803182","https://openalex.org/W6757076751","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W3151736118","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W4362495644","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"We":[0],"posed":[1],"the":[2,20,23],"shared":[3],"task":[4],"of":[5,15,25,30],"assigning":[6],"sentence-level":[7],"quality":[8],"scores":[9],"for":[10],"a":[11],"very":[12],"noisy":[13],"corpus":[14],"sentence":[16],"pairs":[17],"crawled":[18],"from":[19,43],"web,":[21],"with":[22],"goal":[24],"sub-selecting":[26],"1%":[27],"and":[28,48],"10%":[29],"high-quality":[31],"data":[32],"to":[33,36],"be":[34],"used":[35],"train":[37],"machine":[38],"translation":[39],"systems.":[40],"Seventeen":[41],"participants":[42],"companies,":[44],"national":[45],"research":[46],"labs,":[47],"universities":[49],"participated":[50],"in":[51],"this":[52],"task.":[53]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
