{"id":"https://openalex.org/W3120253636","doi":"https://doi.org/10.18653/v1/2020.wmt-1.108","title":"An exploratory approach to the Parallel Corpus Filtering shared task WMT20","display_name":"An exploratory approach to the Parallel Corpus Filtering shared task WMT20","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3120253636","doi":"https://doi.org/10.18653/v1/2020.wmt-1.108","mag":"3120253636"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.108","pdf_url":"https://aclanthology.org/2020.wmt-1.108.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.108.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054573398","display_name":"Ankur Kejriwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Kejriwal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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":0.8253968954086304},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.7775366306304932},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6985855102539062},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6915050745010376},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6253411173820496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6171904802322388},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6082720756530762},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6044643521308899},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5515119433403015},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.541366457939148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42808467149734497},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14975139498710632},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.127208411693573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253968954086304},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7775366306304932},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6985855102539062},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6915050745010376},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6253411173820496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171904802322388},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6082720756530762},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6044643521308899},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5515119433403015},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.541366457939148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42808467149734497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14975139498710632},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.127208411693573},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.108","pdf_url":"https://aclanthology.org/2020.wmt-1.108.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":"mag:3120253636","is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2020.wmt-1.108.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.108","pdf_url":"https://aclanthology.org/2020.wmt-1.108.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":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3120253636.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2933138175","https://openalex.org/W2962735107","https://openalex.org/W2963250244","https://openalex.org/W2963281280","https://openalex.org/W2963626623","https://openalex.org/W2963631907","https://openalex.org/W2963919854","https://openalex.org/W2970155092","https://openalex.org/W2970686691","https://openalex.org/W2970858854","https://openalex.org/W3034938700","https://openalex.org/W3119872155"],"related_works":["https://openalex.org/W2970185230","https://openalex.org/W2902127193","https://openalex.org/W2970963247","https://openalex.org/W2903035303","https://openalex.org/W2902969394","https://openalex.org/W2903490366","https://openalex.org/W3119590346","https://openalex.org/W2903151286","https://openalex.org/W2903182367","https://openalex.org/W3119872155","https://openalex.org/W2970156971","https://openalex.org/W2970858854","https://openalex.org/W2902918014","https://openalex.org/W3096972693","https://openalex.org/W2964240726","https://openalex.org/W2970463863","https://openalex.org/W3120708494","https://openalex.org/W1814624322","https://openalex.org/W2508803094","https://openalex.org/W3119309373"],"abstract_inverted_index":{"In":[0],"this":[1],"document":[2],"we":[3],"describe":[4],"our":[5],"submission":[6],"to":[7,45],"the":[8,30,35,47,53,59],"parallel":[9],"corpus":[10],"filtering":[11,26,43],"task":[12],"using":[13],"multilingual":[14],"word":[15],"embedding,":[16],"language":[17,38,64],"models":[18,39],"and":[19,24,34,51],"an":[20,56],"ensemble":[21],"of":[22,32,37],"pre":[23],"post":[25],"rules.":[27],"We":[28],"use":[29],"norms":[31],"embedding":[33],"perplexities":[36],"along":[40],"with":[41],"pre/post":[42],"rules":[44],"complement":[46],"LASER":[48],"baseline":[49],"scores":[50],"in":[52,62],"end":[54],"get":[55],"improvement":[57],"on":[58],"dev":[60],"set":[61],"both":[63],"pairs.":[65]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-01-18T00:00:00"}