{"id":"https://openalex.org/W2902949028","doi":"https://doi.org/10.18653/v1/w18-6477","title":"An Unsupervised System for Parallel Corpus Filtering","display_name":"An Unsupervised System for Parallel Corpus Filtering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902949028","doi":"https://doi.org/10.18653/v1/w18-6477","mag":"2902949028"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6477","pdf_url":"https://www.aclweb.org/anthology/W18-6477.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6477.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090950630","display_name":"Viktor Hangya","orcid":"https://orcid.org/0000-0002-5144-3069"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viktor Hangya","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101957153","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-4891-682X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Center for Information and Language Processing LMU Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing LMU Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"882","last_page":"887"},"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":0.9941999912261963,"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":0.8710769414901733},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7445030808448792},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7335778474807739},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6751174926757812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6573092341423035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6322247385978699},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5948939919471741},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5511283278465271},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5400477647781372},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4696202576160431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3714696764945984},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08471435308456421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710769414901733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7445030808448792},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7335778474807739},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6751174926757812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6573092341423035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6322247385978699},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5948939919471741},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5511283278465271},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5400477647781372},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4696202576160431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3714696764945984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08471435308456421},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6477","pdf_url":"https://www.aclweb.org/anthology/W18-6477.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/w18-6477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6477","pdf_url":"https://www.aclweb.org/anthology/W18-6477.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":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902949028.pdf","grobid_xml":"https://content.openalex.org/works/W2902949028.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1834000468","https://openalex.org/W2042281163","https://openalex.org/W2124807415","https://openalex.org/W2141440284","https://openalex.org/W2153488166","https://openalex.org/W2257408573","https://openalex.org/W2493916176","https://openalex.org/W2496235729","https://openalex.org/W2511852057","https://openalex.org/W2574026469","https://openalex.org/W2593864460","https://openalex.org/W2595715041","https://openalex.org/W2756978580","https://openalex.org/W2773493195","https://openalex.org/W2804625779","https://openalex.org/W2902918014","https://openalex.org/W2963118869","https://openalex.org/W2963366389","https://openalex.org/W2964343359","https://openalex.org/W4299579390","https://openalex.org/W4299585995"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W3151736118","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W4362495644","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"In":[0],"this":[1,50],"paper":[2],"we":[3,71],"describe":[4],"LMU":[5],"Munich's":[6],"submission":[7],"for":[8,36,45],"the":[9,19,38,98,102,112],"WMT":[10],"2018":[11],"Parallel":[12],"Corpus":[13],"Filtering":[14],"shared":[15,103],"task":[16,27],"which":[17],"addresses":[18],"problem":[20,51],"of":[21,28,40,101],"cleaning":[22,31],"noisy":[23,69],"parallel":[24,32,119],"corpora.":[25],"The":[26],"mining":[29],"and":[30,80],"sentences":[33],"is":[34],"important":[35],"improving":[37],"quality":[39],"machine":[41],"translation":[42],"systems,":[43,114],"especially":[44],"low-resource":[46],"languages.":[47],"We":[48],"tackle":[49],"in":[52],"a":[53,107],"fully":[54],"unsupervised":[55,92],"fashion":[56],"relying":[57],"on":[58],"bilingual":[59,65,77],"word":[60],"embeddings":[61],"created":[62],"without":[63],"any":[64,118],"signal.":[66],"After":[67],"pre-filtering":[68],"data":[70,84],"rank":[72],"sentence":[73],"pairs":[74],"by":[75,85],"calculating":[76],"sentence-level":[78],"similarities":[79],"then":[81],"remove":[82],"redundant":[83],"employing":[86],"monolingual":[87],"similarity":[88],"as":[89],"well.":[90],"Our":[91],"system":[93],"achieved":[94],"good":[95],"performance":[96],"during":[97],"official":[99],"evaluation":[100],"task,":[104],"scoring":[105],"only":[106],"few":[108],"BLEU":[109],"points":[110],"behind":[111],"best":[113],"while":[115],"not":[116],"requiring":[117],"training":[120],"data.":[121]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}