{"id":"https://openalex.org/W2970908867","doi":"https://doi.org/10.18653/v1/w19-5438","title":"Noisy Parallel Corpus Filtering through Projected Word Embeddings","display_name":"Noisy Parallel Corpus Filtering through Projected Word Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970908867","doi":"https://doi.org/10.18653/v1/w19-5438","mag":"2970908867"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5438","pdf_url":"https://www.aclweb.org/anthology/W19-5438.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5438.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002870078","display_name":"Murathan Kurfal\u0131","orcid":"https://orcid.org/0000-0002-7020-8275"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Murathan Kurfal\u0131","raw_affiliation_strings":["Department of Linguistics Stockholm University"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics Stockholm University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103282437","display_name":"Robert \u00d6stling","orcid":"https://orcid.org/0000-0002-6027-4156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert \u00d6stling","raw_affiliation_strings":["Department of Linguistics Stockholm University"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics Stockholm University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002870078"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82310666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"281"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.8455466032028198},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7366258502006531},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.7274890542030334},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.694934606552124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6205488443374634},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6092553734779358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867816209793091},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5441149473190308},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5356997847557068},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5103799700737},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4665026068687439},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20937970280647278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10880598425865173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8455466032028198},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7366258502006531},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.7274890542030334},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.694934606552124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6205488443374634},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6092553734779358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867816209793091},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5441149473190308},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5356997847557068},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5103799700737},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4665026068687439},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20937970280647278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10880598425865173},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-5438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5438","pdf_url":"https://www.aclweb.org/anthology/W19-5438.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5438","pdf_url":"https://www.aclweb.org/anthology/W19-5438.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 Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970908867.pdf","grobid_xml":"https://content.openalex.org/works/W2970908867.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2157133710","https://openalex.org/W2250606284","https://openalex.org/W2493916176","https://openalex.org/W2538358357","https://openalex.org/W2773493195","https://openalex.org/W2798389157","https://openalex.org/W2902918014","https://openalex.org/W2903061071","https://openalex.org/W2913659301","https://openalex.org/W2963118869","https://openalex.org/W2973088264","https://openalex.org/W3010805239","https://openalex.org/W4288601832","https://openalex.org/W4299579390"],"related_works":["https://openalex.org/W2368019753","https://openalex.org/W2333930193","https://openalex.org/W2737356002","https://openalex.org/W2246241526","https://openalex.org/W4301122218","https://openalex.org/W2374150061","https://openalex.org/W2081340182","https://openalex.org/W158195847","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"very":[3],"simple":[4],"method":[5],"for":[6],"parallel":[7],"text":[8],"cleaning":[9],"of":[10,16,29],"low-resource":[11],"languages,":[12],"based":[13],"on":[14,20],"projection":[15],"word":[17],"embeddings":[18],"trained":[19],"large":[21],"monolingual":[22],"corpora":[23],"in":[24,38],"high-resource":[25],"languages.":[26],"In":[27],"spite":[28],"its":[30],"simplicity,":[31],"we":[32],"approach":[33],"the":[34,39],"strong":[35],"baseline":[36],"system":[37],"downstream":[40],"machine":[41],"translation":[42],"evaluation.":[43]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
