{"id":"https://openalex.org/W2902009742","doi":"https://doi.org/10.18653/v1/w18-6479","title":"The JHU Parallel Corpus Filtering Systems for WMT 2018","display_name":"The JHU Parallel Corpus Filtering Systems for WMT 2018","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902009742","doi":"https://doi.org/10.18653/v1/w18-6479","mag":"2902009742"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6479","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6479","pdf_url":"https://www.aclweb.org/anthology/W18-6479.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/W18-6479.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Huda Khayrallah","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034399968","display_name":"Hainan Xu","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":"Hainan Xu","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University"],"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"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080544452"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.4659,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86893959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"899"},"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9941999912261963,"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":0.780921220779419},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.7109668254852295},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.67027747631073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6614044904708862},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.635554313659668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5967581272125244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5784523487091064},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.47412657737731934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.416304349899292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09711498022079468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780921220779419},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7109668254852295},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.67027747631073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6614044904708862},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.635554313659668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5967581272125244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5784523487091064},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.47412657737731934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.416304349899292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09711498022079468},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w18-6479","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6479","pdf_url":"https://www.aclweb.org/anthology/W18-6479.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/f33105b6-1df7-4826-b734-8e5527e8f88b","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/f33105b6-1df7-4826-b734-8e5527e8f88b","pdf_url":"http://www.aclweb.org/anthology/W18-6479","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"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/f33105b6-1df7-4826-b734-8e5527e8f88b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f33105b6-1df7-4826-b734-8e5527e8f88b","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Khayrallah, H, Xu, H & Koehn, P 2018, The JHU Parallel Corpus Filtering Systems for WMT 2018. in Proceedings of the Third Conference on Machine Translation: Shared Task Papers. Belgium, Brussels, pp. 896-899, EMNLP 2018 Third Conference on Machine Translation (WMT18), Brussels, Belgium, 31/10/18. https://doi.org/10.18653/v1/W18-64106","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6479","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6479","pdf_url":"https://www.aclweb.org/anthology/W18-6479.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902009742.pdf","grobid_xml":"https://content.openalex.org/works/W2902009742.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1834000468","https://openalex.org/W2101234009","https://openalex.org/W2110006374","https://openalex.org/W2117278770","https://openalex.org/W2129734311","https://openalex.org/W2134800885","https://openalex.org/W2136477195","https://openalex.org/W2147262247","https://openalex.org/W2155607551","https://openalex.org/W2186890008","https://openalex.org/W2773493195","https://openalex.org/W2963506925","https://openalex.org/W2963919854","https://openalex.org/W3098663719","https://openalex.org/W3201817155","https://openalex.org/W3203064768"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2002616876","https://openalex.org/W3174418441","https://openalex.org/W4309298167"],"abstract_inverted_index":{"This":[0,54],"work":[1,55],"describes":[2],"our":[3],"submission":[4],"to":[5,68,71],"the":[6,20,48,51,65,73],"WMT18":[7],"Parallel":[8],"Corpus":[9,22],"Filtering":[10,23],"shared":[11],"task.":[12],"We":[13],"use":[14,43],"a":[15,35,39,44],"slightly":[16],"modified":[17],"version":[18],"of":[19,47],"Zipporah":[21,58],"toolkit":[24],"(Xu":[25],"and":[26,34,42,76],"Koehn,":[27],"2017),":[28],"which":[29],"computes":[30],"an":[31],"adequacy":[32],"score":[33,37],"fluency":[36],"on":[38],"sentence":[40],"pair,":[41],"weighted":[45],"sum":[46],"scores":[49],"as":[50,82],"selection":[52],"criteria.":[53],"differs":[56],"from":[57],"in":[59,83],"that":[60],"we":[61],"experiment":[62],"with":[63],"using":[64],"noisy":[66],"corpus":[67],"be":[69],"filtered":[70],"compute":[72],"combination":[74],"weights,":[75],"thus":[77],"avoids":[78],"generating":[79],"synthetic":[80],"data":[81],"standard":[84],"Zipporah.":[85]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}