{"id":"https://openalex.org/W7126373965","doi":"https://doi.org/10.18653/v1/2020.wmt-1.107","title":"Bicleaner at WMT 2020: Universitat d\u2019Alacant-Prompsit\u2019s submission to the parallel corpus filtering shared task","display_name":"Bicleaner at WMT 2020: Universitat d\u2019Alacant-Prompsit\u2019s submission to the parallel corpus filtering shared task","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W7126373965","doi":"https://doi.org/10.18653/v1/2020.wmt-1.107"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.107","pdf_url":"https://aclanthology.org/2020.wmt-1.107.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047512371","display_name":"Miquel Espl\u00e0-Gomis","orcid":"https://orcid.org/0000-0002-2682-066X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miquel Espl\u00e0-Gomis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060497847","display_name":"V\u00edctor M. S\u00e1nchez-Cartagena","orcid":"https://orcid.org/0000-0001-9600-6885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V\u00edctor M. S\u00e1nchez-Cartagena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059502541","display_name":"Jaume Zaragoza-Bernabeu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaume Zaragoza-Bernabeu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124471967","display_name":"Felipe S\u00e1nchez-Mart\u00ednez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felipe S\u00e1nchez-Mart\u00ednez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50992137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"952","last_page":"958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.3018999993801117,"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/T13629","display_name":"Text Readability and Simplification","score":0.3018999993801117,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.13830000162124634,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.1257999986410141,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.32170000672340393},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.31049999594688416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30090001225471497},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.28459998965263367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5895000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3653999865055084},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.107","pdf_url":"https://aclanthology.org/2020.wmt-1.107.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.107","pdf_url":"https://aclanthology.org/2020.wmt-1.107.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":[{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6458387989","display_name":"Global Under-Resourced MEedia Translation","funder_award_id":"825299","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/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335813","display_name":"Innovation and Networks Executive Agency","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126373965.pdf","grobid_xml":"https://content.openalex.org/works/W7126373965.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,14,26,43,46,49,64,69,79],"joint":[4],"submission":[5],"of":[6,45,81],"Universitat":[7],"d'Alacant":[8],"and":[9,36,71,87],"Prompsit":[10],"Language":[11],"Engineering":[12],"to":[13,52],"WMT":[15],"2020":[16],"shared":[17],"task":[18,70],"on":[19,25],"parallel":[20,50,74],"corpus":[21],"filtering.Our":[22],"submission,":[23],"based":[24],"free/open-source":[27],"tool":[28],"Bicleaner,":[29],"enhances":[30],"it":[31],"with":[32],"Extremely":[33],"Randomised":[34],"Trees":[35],"lexical":[37],"similarity":[38],"features":[39],"that":[40],"account":[41],"for":[42,68],"frequency":[44],"words":[47],"in":[48],"sentences":[51,56],"determine":[53],"if":[54],"two":[55],"are":[57],"parallel.To":[58],"train":[59],"this":[60],"classifier":[61],"we":[62,77],"used":[63],"clean":[65],"corpora":[66],"provided":[67],"synthetic":[72],"noisy":[73],"sentences.In":[75],"addition":[76],"rescore":[78],"output":[80],"Bicleaner":[82],"using":[83],"characterlevel":[84],"language":[85],"models":[86],"n-gram":[88],"saturation.":[89]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}
