{"id":"https://openalex.org/W2903035303","doi":"https://doi.org/10.18653/v1/w18-6488","title":"Prompsit\u2019s submission to WMT 2018 Parallel Corpus Filtering shared task","display_name":"Prompsit\u2019s submission to WMT 2018 Parallel Corpus Filtering shared task","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2903035303","doi":"https://doi.org/10.18653/v1/w18-6488","mag":"2903035303"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6488","pdf_url":"https://www.aclweb.org/anthology/W18-6488.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6488.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"V\u00edctor M. S\u00e1nchez-Cartagena","raw_affiliation_strings":["Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain"],"affiliations":[{"raw_affiliation_string":"Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035819093","display_name":"Marta Ba\u00f1\u00f3n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marta Ba\u00f1\u00f3n","raw_affiliation_strings":["Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain"],"affiliations":[{"raw_affiliation_string":"Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027802795","display_name":"Sergio Ortiz-Rojas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergio Ortiz-Rojas","raw_affiliation_strings":["Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain"],"affiliations":[{"raw_affiliation_string":"Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604967","display_name":"Gema Ram\u00edrez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gema Ram\u00edrez","raw_affiliation_strings":["Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain"],"affiliations":[{"raw_affiliation_string":"Prompsit Language Engineering Av. Universitat s/n. Edifici Quorum III E-03202 Elx, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060497847"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7009,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96807491,"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":"955","last_page":"962"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9962000250816345,"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":0.8619157075881958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6935299038887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6833968162536621},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6466504335403442},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6303165555000305},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5250059366226196},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5062936544418335},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.46716201305389404},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4497879445552826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41744425892829895},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12373954057693481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619157075881958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6935299038887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833968162536621},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6466504335403442},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6303165555000305},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5250059366226196},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5062936544418335},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.46716201305389404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4497879445552826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41744425892829895},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12373954057693481},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6488","pdf_url":"https://www.aclweb.org/anthology/W18-6488.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/w18-6488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6488","pdf_url":"https://www.aclweb.org/anthology/W18-6488.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":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903035303.pdf","grobid_xml":"https://content.openalex.org/works/W2903035303.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1905522558","https://openalex.org/W1973152633","https://openalex.org/W2105410942","https://openalex.org/W2107695330","https://openalex.org/W2134800885","https://openalex.org/W2141440284","https://openalex.org/W2159755860","https://openalex.org/W2164766438","https://openalex.org/W2218630638","https://openalex.org/W2572136474","https://openalex.org/W2609278920","https://openalex.org/W2767899794","https://openalex.org/W2902918014","https://openalex.org/W2911964244","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963661177","https://openalex.org/W2964343359"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2787311093","https://openalex.org/W2532616038","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2057384730","https://openalex.org/W2008468404","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"Prompsit":[3],"Language":[4],"Engineering's":[5],"submissions":[6,18,78],"to":[7],"the":[8,49,88],"WMT":[9],"2018":[10],"parallel":[11],"corpus":[12,59],"filtering":[13],"shared":[14],"task.":[15],"Our":[16,77],"four":[17],"were":[19,46,79],"based":[20],"on":[21,87],"an":[22,69],"automatic":[23],"classifier":[24],"for":[25,40,55],"identifying":[26],"pairs":[27],"of":[28,36],"sentences":[29,42],"that":[30],"are":[31],"mutual":[32],"translations.":[33],"A":[34],"set":[35],"hand-crafted":[37],"hard":[38],"rules":[39],"discarding":[41],"with":[43,60,84],"evident":[44],"flaws":[45],"applied":[47],"before":[48],"classifier.":[50],"We":[51],"explored":[52],"different":[53],"strategies":[54],"achieving":[56],"a":[57],"training":[58,92],"diverse":[61],"vocabulary":[62],"and":[63,74],"fluent":[64],"sentences:":[65],"language":[66],"model":[67],"scoring,":[68],"active-learning-inspired":[70],"data":[71],"selection":[72],"algorithm":[73],"n-gram":[75],"saturation.":[76],"very":[80],"competitive":[81],"in":[82],"comparison":[83],"other":[85],"participants":[86],"100":[89],"million":[90],"word":[91],"corpus.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}