{"id":"https://openalex.org/W2970559709","doi":"https://doi.org/10.18653/v1/w19-5436","title":"Quality and Coverage: The AFRL Submission to the WMT19 Parallel Corpus Filtering for Low-Resource Conditions Task","display_name":"Quality and Coverage: The AFRL Submission to the WMT19 Parallel Corpus Filtering for Low-Resource Conditions Task","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970559709","doi":"https://doi.org/10.18653/v1/w19-5436","mag":"2970559709"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5436","pdf_url":"https://www.aclweb.org/anthology/W19-5436.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5436.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010930111","display_name":"Grant Erdmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Grant Erdmann","raw_affiliation_strings":["Air Force Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Air Force Research Laboratory","institution_ids":["https://openalex.org/I1280414376"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002603615","display_name":"Jeremy Gwinnup","orcid":"https://orcid.org/0009-0002-8321-9333"},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Gwinnup","raw_affiliation_strings":["Air Force Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Air Force Research Laboratory","institution_ids":["https://openalex.org/I1280414376"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010930111"],"corresponding_institution_ids":["https://openalex.org/I1280414376"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78048195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"270"},"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":0.9997000098228455,"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":0.9909999966621399,"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":0.8117386102676392},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7177460193634033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6764644384384155},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5755718946456909},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5401164293289185},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.537521481513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5118793249130249},{"id":"https://openalex.org/keywords/nepali","display_name":"Nepali","score":0.4966493248939514},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4516734480857849},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4425981640815735},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43946731090545654},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08413589000701904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117386102676392},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7177460193634033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6764644384384155},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5755718946456909},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5401164293289185},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.537521481513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5118793249130249},{"id":"https://openalex.org/C2780068402","wikidata":"https://www.wikidata.org/wiki/Q33823","display_name":"Nepali","level":2,"score":0.4966493248939514},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4516734480857849},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4425981640815735},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43946731090545654},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08413589000701904},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-5436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5436","pdf_url":"https://www.aclweb.org/anthology/W19-5436.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5436","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5436","pdf_url":"https://www.aclweb.org/anthology/W19-5436.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970559709.pdf","grobid_xml":"https://content.openalex.org/works/W2970559709.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2095755718","https://openalex.org/W2116792345","https://openalex.org/W2124807415","https://openalex.org/W2133459682","https://openalex.org/W2250342921","https://openalex.org/W2250931265","https://openalex.org/W2252035278","https://openalex.org/W2515117158","https://openalex.org/W2563351168","https://openalex.org/W2595715041","https://openalex.org/W2773493195","https://openalex.org/W2902867443","https://openalex.org/W2903193068","https://openalex.org/W2963250244","https://openalex.org/W2963626623","https://openalex.org/W2970279348"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W170118632","https://openalex.org/W2518299649","https://openalex.org/W2395641992","https://openalex.org/W3021126373","https://openalex.org/W2251802443","https://openalex.org/W2807475932","https://openalex.org/W4280571180","https://openalex.org/W1619002","https://openalex.org/W3066373881"],"abstract_inverted_index":{"The":[0],"WMT19":[1],"Parallel":[2],"Corpus":[3],"Filtering":[4],"For":[5],"Low-Resource":[6],"Conditions":[7],"Task":[8],"aims":[9],"to":[10,19],"test":[11],"various":[12],"methods":[13,56],"of":[14,40,71],"filtering":[15],"noisy":[16,31],"parallel":[17],"corpora,":[18],"make":[20],"them":[21],"useful":[22],"for":[23],"training":[24],"machine":[25],"translation":[26],"systems.":[27],"This":[28,44],"year":[29],"the":[30,35,47,68],"corpora":[32],"are":[33],"from":[34],"relatively":[36],"low-resource":[37],"language":[38],"pairs":[39],"English-Nepali":[41],"and":[42,57,67],"English-Sinhala.":[43],"papers":[45],"describes":[46],"Air":[48],"Force":[49],"Research":[50],"Laboratory":[51],"(AFRL)":[52],"submissions,":[53],"including":[54],"preprocessing":[55],"scoring":[58],"metrics.":[59],"Numerical":[60],"results":[61],"indicate":[62],"a":[63],"benefit":[64],"over":[65],"baseline":[66],"relative":[69],"effects":[70],"different":[72],"options.":[73]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}