{"id":"https://openalex.org/W2970155092","doi":"https://doi.org/10.18653/v1/w19-5433","title":"Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data","display_name":"Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970155092","doi":"https://doi.org/10.18653/v1/w19-5433","mag":"2970155092"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5433","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w19-5433","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043270586","display_name":"Amittai Axelrod","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amittai Axelrod","raw_affiliation_strings":["DIDI RESEARCH AMERICA LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIDI RESEARCH AMERICA LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074353158","display_name":"Anish Kumar","orcid":"https://orcid.org/0000-0001-9183-7161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anish Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047256575","display_name":"Steve Sloto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Sloto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51966122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9969000220298767,"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":0.7942510843276978},{"id":"https://openalex.org/keywords/laptop","display_name":"Laptop","score":0.6450225114822388},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5464363098144531},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5381250381469727},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.47662389278411865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44932326674461365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3396376669406891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.23811358213424683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942510843276978},{"id":"https://openalex.org/C2780008327","wikidata":"https://www.wikidata.org/wiki/Q3962","display_name":"Laptop","level":2,"score":0.6450225114822388},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5464363098144531},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5381250381469727},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.47662389278411865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44932326674461365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3396376669406891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23811358213424683},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"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/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/w19-5433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5433","pdf_url":null,"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/w19-5433","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5433","pdf_url":null,"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":[{"display_name":"Decent work and economic growth","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1560656908","https://openalex.org/W1905522558","https://openalex.org/W2087596289","https://openalex.org/W2101105183","https://openalex.org/W2117278770","https://openalex.org/W2134800885","https://openalex.org/W2508809683","https://openalex.org/W2751885040","https://openalex.org/W2860784415","https://openalex.org/W2869941219","https://openalex.org/W2902831278","https://openalex.org/W2902867443","https://openalex.org/W2902918014","https://openalex.org/W2903297715","https://openalex.org/W2913659301","https://openalex.org/W2939335894","https://openalex.org/W2946379889","https://openalex.org/W2957392020","https://openalex.org/W2962735107","https://openalex.org/W2963250244","https://openalex.org/W2963281280","https://openalex.org/W2970858854"],"related_works":["https://openalex.org/W3153292769","https://openalex.org/W2045444909","https://openalex.org/W1516398359","https://openalex.org/W1901656956","https://openalex.org/W2990805456","https://openalex.org/W2941659365","https://openalex.org/W4239210160","https://openalex.org/W2376300433","https://openalex.org/W4242605858","https://openalex.org/W2994927414"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,12,16,44,82],"purely":[3],"monolingual":[4,46],"approach":[5,75],"to":[6,30,70],"filtering":[7,66],"for":[8,32],"parallel":[9,36],"data":[10,37,53],"from":[11,51],"noisy":[13],"corpus":[14],"in":[15,85],"low-resource":[17],"scenario.":[18],"Our":[19,40,74],"work":[20],"is":[21,38,43,57,76],"inspired":[22],"by":[23],"Junczysdowmunt:2018,":[24],"but":[25],"we":[26],"relax":[27],"the":[28,63],"requirements":[29],"allow":[31],"cases":[33],"where":[34],"no":[35],"available.":[39],"primary":[41],"contribution":[42],"dual":[45],"cross-entropy":[47],"delta":[48],"criterion":[49],"modified":[50],"Cynical":[52],"selection":[54],"Axelrod:2017,":[55],"and":[56,78],"competitive":[58],"(within":[59],"1.8":[60],"BLEU)":[61],"with":[62],"best":[64],"bilingual":[65],"method":[67],"when":[68],"used":[69],"train":[71],"SMT":[72],"systems.":[73],"featherweight,":[77],"runs":[79],"end-to-end":[80],"on":[81],"standard":[83],"laptop":[84],"three":[86],"hours.":[87]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}