{"id":"https://openalex.org/W3098515495","doi":"https://doi.org/10.18653/v1/2020.wmt-1.106","title":"Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions","display_name":"Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3098515495","doi":"https://doi.org/10.18653/v1/2020.wmt-1.106","mag":"3098515495"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.106","pdf_url":"https://aclanthology.org/2020.wmt-1.106.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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.106.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073249931","display_name":"Muhammad ElNokrashy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad ElNokrashy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007758583","display_name":"Amr Hendy","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":false,"raw_author_name":"Amr Hendy","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040098231","display_name":"Mohamed Abdelghaffar","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":false,"raw_author_name":"Mohamed Abdelghaffar","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021938376","display_name":"Mohamed Afify","orcid":"https://orcid.org/0000-0002-4445-9767"},"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":false,"raw_author_name":"Mohamed Afify","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048873489","display_name":"Ahmed Y. Tawfik","orcid":"https://orcid.org/0000-0003-3561-3248"},"institutions":[{"id":"https://openalex.org/I133837150","display_name":"University of Huddersfield","ror":"https://ror.org/05t1h8f27","country_code":"GB","type":"education","lineage":["https://openalex.org/I133837150"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed Tawfik","raw_affiliation_strings":["University of Huddersfield, Huddersfield, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Huddersfield, Huddersfield, United Kingdom","institution_ids":["https://openalex.org/I133837150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030937723","display_name":"Hany Hassan Awadalla","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":false,"raw_author_name":"Hany Hassan Awadalla","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1301,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56294724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"947","last_page":"951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9955000281333923,"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":0.7129659652709961},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6709764003753662},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.644458532333374},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6284494996070862},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6269187927246094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5772109627723694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564249753952026},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5060035586357117},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48050153255462646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08977550268173218},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08691051602363586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129659652709961},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6709764003753662},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.644458532333374},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6284494996070862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6269187927246094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5772109627723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564249753952026},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5060035586357117},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48050153255462646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08977550268173218},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08691051602363586},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.106","pdf_url":"https://aclanthology.org/2020.wmt-1.106.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":"pmh:oai:arXiv.org:2011.07933","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07933","pdf_url":"https://arxiv.org/pdf/2011.07933","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":null,"raw_type":"text"},{"id":"mag:3098515495","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.07933v1","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.2011.07933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.07933","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3118434027","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.07933","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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.106","pdf_url":"https://aclanthology.org/2020.wmt-1.106.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/W3098515495.pdf","grobid_xml":"https://content.openalex.org/works/W3098515495.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2593864460","https://openalex.org/W2952509486","https://openalex.org/W2962735107","https://openalex.org/W2963919854","https://openalex.org/W3001434439","https://openalex.org/W3025490068"],"related_works":["https://openalex.org/W3118434027","https://openalex.org/W3119188361","https://openalex.org/W2917025446","https://openalex.org/W2127293685","https://openalex.org/W2917098612","https://openalex.org/W2464151748","https://openalex.org/W2395971734","https://openalex.org/W3120955312","https://openalex.org/W2000026602","https://openalex.org/W9218159","https://openalex.org/W2957558225","https://openalex.org/W2963842834","https://openalex.org/W2395386636","https://openalex.org/W2463861136","https://openalex.org/W2740984590","https://openalex.org/W2759035416","https://openalex.org/W2970950209","https://openalex.org/W3034775979","https://openalex.org/W2003484529","https://openalex.org/W2092910966"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,33,38,40,45,56,62],"description":[4],"of":[5],"our":[6,47],"submission":[7],"to":[8,26],"WMT20":[9],"sentence":[10],"filtering":[11],"task.We":[12],"combine":[13],"scores":[14,35],"from":[15],"custom":[16],"LASER":[17],"built":[18,25],"for":[19,65],"each":[20],"source":[21],"language,":[22],"a":[23],"classifier":[24],"distinguish":[27],"positive":[28],"and":[29,32,51,67],"negative":[30],"pairs":[31],"original":[34],"provided":[36,43],"with":[37],"task.For":[39],"mBART":[41],"setup,":[42],"by":[44],"organizers,":[46],"method":[48],"shows":[49],"7%":[50],"5%":[52],"relative":[53],"improvement,":[54],"over":[55],"baseline,":[57],"in":[58],"sacreBLEU":[59],"score":[60],"on":[61],"test":[63],"set":[64],"Pashto":[66],"Khmer":[68],"respectively.":[69]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-11-23T00:00:00"}