{"id":"https://openalex.org/W2902319873","doi":"https://doi.org/10.18653/v1/w18-6487","title":"The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task","display_name":"The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902319873","doi":"https://doi.org/10.18653/v1/w18-6487","mag":"2902319873"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6487","pdf_url":"https://www.aclweb.org/anthology/W18-6487.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6487.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063680910","display_name":"Nick Rossenbach","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nick Rossenbach","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082142903","display_name":"Jan Rosendahl","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Rosendahl","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005673540","display_name":"Yunsu Kim","orcid":"https://orcid.org/0000-0002-1375-005X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113879206","display_name":"Miguel Gra\u00e7a","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Miguel Gra\u00e7a","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055209653","display_name":"Aman Gokrani","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aman Gokrani","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":2.0371,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90850477,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"946","last_page":"954"},"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":0.993399977684021,"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":0.8575753569602966},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7493013143539429},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6794689297676086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.671559751033783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6504967212677002},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6317844390869141},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6208726167678833},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5642112493515015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.506477952003479},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5055761337280273},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48953136801719666},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.44523176550865173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8575753569602966},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7493013143539429},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6794689297676086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671559751033783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6504967212677002},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6317844390869141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6208726167678833},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5642112493515015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.506477952003479},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5055761337280273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48953136801719666},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.44523176550865173},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6487","pdf_url":"https://www.aclweb.org/anthology/W18-6487.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"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6487","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6487","pdf_url":"https://www.aclweb.org/anthology/W18-6487.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":0.75}],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"Horizon2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902319873.pdf","grobid_xml":"https://content.openalex.org/works/W2902319873.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1647671624","https://openalex.org/W2006969979","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2097927681","https://openalex.org/W2101105183","https://openalex.org/W2101207453","https://openalex.org/W2113021982","https://openalex.org/W2124807415","https://openalex.org/W2141440284","https://openalex.org/W2149327368","https://openalex.org/W2156985047","https://openalex.org/W2186615578","https://openalex.org/W2294059674","https://openalex.org/W2384495648","https://openalex.org/W2595715041","https://openalex.org/W2758605572","https://openalex.org/W2778814079","https://openalex.org/W2902786662","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2964343359","https://openalex.org/W3082674894","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W170118632","https://openalex.org/W2395641992","https://openalex.org/W3021126373","https://openalex.org/W2807475932","https://openalex.org/W4280571180","https://openalex.org/W3066373881","https://openalex.org/W2903057408","https://openalex.org/W92588874","https://openalex.org/W2426188458"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,10,17,83],"submission":[4],"of":[5,16,97],"RWTH":[6],"Aachen":[7],"University":[8],"for":[9],"DeEn":[11],"parallel":[12],"corpus":[13,69],"filtering":[14,70,104],"task":[15],"EMNLP":[18],"2018":[19],"Third":[20],"Conference":[21],"on":[22,73,82,89,100],"Machine":[23],"Translation":[24],"(WMT":[25],"2018).":[26],"We":[27],"use":[28],"several":[29],"rule-based,":[30],"heuristic":[31],"methods":[32],"to":[33,54],"preselect":[34],"sentence":[35,38],"pairs.":[36],"These":[37],"pairs":[39],"are":[40],"scored":[41],"with":[42],"count-based":[43],"and":[44,49,78,105],"neural":[45,75],"systems":[46],"as":[47],"language":[48,76],"translation":[50,79],"models.":[51],"In":[52],"addition":[53],"single":[55],"sentence-pair":[56],"scoring,":[57],"we":[58,108],"further":[59],"implement":[60],"a":[61,95],"simple":[62],"redundancy":[63],"removing":[64],"heuristic.":[65],"Our":[66],"best":[67],"performing":[68],"system":[71],"relies":[72],"recurrent":[74],"models":[77,80],"based":[81],"transformer":[84],"architecture.":[85],"A":[86],"model":[87],"trained":[88],"10M":[90],"randomly":[91],"sampled":[92],"tokens":[93],"reaches":[94],"performance":[96],"9.2%":[98],"BLEU":[99],"newstest2018.":[101],"Using":[102],"our":[103],"ranking":[106],"techniques":[107],"achieve":[109],"34.8%":[110],"BLEU.":[111]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}
