{"id":"https://openalex.org/W2798389157","doi":"https://doi.org/10.18653/v1/p18-2037","title":"Filtering and Mining Parallel Data in a Joint Multilingual Space","display_name":"Filtering and Mining Parallel Data in a Joint Multilingual Space","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798389157","doi":"https://doi.org/10.18653/v1/p18-2037","mag":"2798389157"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2037","pdf_url":"https://www.aclweb.org/anthology/P18-2037.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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/P18-2037.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015857371"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":11.0761,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98591753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"234"},"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":0.9876000285148621,"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":0.8699737191200256},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7861107587814331},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6862862706184387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6805409789085388},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6364825963973999},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.634392499923706},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5987810492515564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5702745318412781},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5496925711631775},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5272946357727051},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.493873655796051},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48686686158180237},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4760686755180359},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41248995065689087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699737191200256},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7861107587814331},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6862862706184387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6805409789085388},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6364825963973999},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.634392499923706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5987810492515564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702745318412781},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5496925711631775},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5272946357727051},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.493873655796051},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48686686158180237},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4760686755180359},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41248995065689087},{"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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2037","pdf_url":"https://www.aclweb.org/anthology/P18-2037.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2037","pdf_url":"https://www.aclweb.org/anthology/P18-2037.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798389157.pdf","grobid_xml":"https://content.openalex.org/works/W2798389157.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1905522558","https://openalex.org/W1973152633","https://openalex.org/W2047295649","https://openalex.org/W2107695330","https://openalex.org/W2142074148","https://openalex.org/W2166098990","https://openalex.org/W2251805974","https://openalex.org/W2311921240","https://openalex.org/W2513660799","https://openalex.org/W2514567832","https://openalex.org/W2525778437","https://openalex.org/W2550821151","https://openalex.org/W2593864460","https://openalex.org/W2609278920","https://openalex.org/W2613904329","https://openalex.org/W2739740656","https://openalex.org/W2794365787","https://openalex.org/W2939335894","https://openalex.org/W2951184134","https://openalex.org/W2962784628","https://openalex.org/W2963216553","https://openalex.org/W2963251942","https://openalex.org/W2963366389","https://openalex.org/W2963403868","https://openalex.org/W2963672008","https://openalex.org/W2964265128","https://openalex.org/W4299585995","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2597655663","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"We":[0,31],"learn":[1],"a":[2,36],"joint":[3],"multilingual":[4],"sentence":[5],"embedding":[6],"and":[7,21,70],"use":[8],"the":[9,40,54,67,76],"distance":[10],"between":[11],"sentences":[12,83],"in":[13,27,84],"different":[14],"languages":[15],"to":[16,22,34,43,62,71,80],"filter":[17],"noisy":[18],"parallel":[19,25,82],"data":[20,26],"mine":[23,63],"for":[24,66],"large":[28],"news":[29],"collections.":[30],"are":[32],"able":[33],"improve":[35],"competitive":[37,73],"baseline":[38],"on":[39,75],"WMT'14":[41,68],"English":[42],"German":[44],"task":[45,79],"by":[46,49],"0.3":[47],"BLEU":[48],"filtering":[50],"out":[51],"25%":[52],"of":[53],"training":[55],"data.":[56],"The":[57],"same":[58],"approach":[59],"is":[60],"used":[61],"additional":[64],"bitexts":[65],"system":[69],"obtain":[72],"results":[74],"BUCC":[77],"shared":[78],"identify":[81],"comparable":[85],"corpora.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}