{"id":"https://openalex.org/W2902831278","doi":"https://doi.org/10.18653/v1/w18-6473","title":"STACC, OOV Density and N-gram Saturation: Vicomtech\u2019s Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering","display_name":"STACC, OOV Density and N-gram Saturation: Vicomtech\u2019s Participation in the WMT 2018 Shared Task on Parallel Corpus Filtering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902831278","doi":"https://doi.org/10.18653/v1/w18-6473","mag":"2902831278"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6473","pdf_url":"https://www.aclweb.org/anthology/W18-6473.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/W18-6473.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085424842","display_name":"Andoni Azpeitia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100188","display_name":"Biogipuzkoa Health Research Institute","ror":"https://ror.org/01a2wsa50","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210100188"]},{"id":"https://openalex.org/I4210121184","display_name":"Policl\u00ednica Gipuzkoa","ror":"https://ror.org/02rjkjw28","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210121184"]},{"id":"https://openalex.org/I4210149720","display_name":"Diputaci\u00f3n Foral de Gipuzkoa","ror":"https://ror.org/05bvkb649","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210149720"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andoni Azpeitia","raw_affiliation_strings":["Donostia / San Sebastin, Gipuzkoa, Spain","Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donostia / San Sebastin, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210100188","https://openalex.org/I4210121184","https://openalex.org/I4210149720"]},{"raw_affiliation_string":"Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087412588","display_name":"Thierry Etchegoyhen","orcid":"https://orcid.org/0000-0001-7253-1693"},"institutions":[{"id":"https://openalex.org/I4210100188","display_name":"Biogipuzkoa Health Research Institute","ror":"https://ror.org/01a2wsa50","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210100188"]},{"id":"https://openalex.org/I4210121184","display_name":"Policl\u00ednica Gipuzkoa","ror":"https://ror.org/02rjkjw28","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210121184"]},{"id":"https://openalex.org/I4210149720","display_name":"Diputaci\u00f3n Foral de Gipuzkoa","ror":"https://ror.org/05bvkb649","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210149720"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Thierry Etchegoyhen","raw_affiliation_strings":["Donostia / San Sebastin, Gipuzkoa, Spain","Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donostia / San Sebastin, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210100188","https://openalex.org/I4210121184","https://openalex.org/I4210149720"]},{"raw_affiliation_string":"Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055241434","display_name":"Eva Mart\u00ednez Garc\u00eda","orcid":"https://orcid.org/0000-0002-1071-8230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eva Mart\u00ednez Garcia","raw_affiliation_strings":["Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donostia / San Sebasti\u00e1n, Gipuzkoa, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3396,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62514739,"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":"860","last_page":"866"},"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":0.9988999962806702,"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":0.8324646949768066},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7954791188240051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.690723717212677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5914665460586548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5755367279052734},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5748504996299744},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5326606631278992},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5089664459228516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4767804443836212},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32876598834991455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324646949768066},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7954791188240051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.690723717212677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5914665460586548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755367279052734},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5748504996299744},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5326606631278992},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5089664459228516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4767804443836212},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32876598834991455},{"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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6473","pdf_url":"https://www.aclweb.org/anthology/W18-6473.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/w18-6473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6473","pdf_url":"https://www.aclweb.org/anthology/W18-6473.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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902831278.pdf","grobid_xml":"https://content.openalex.org/works/W2902831278.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1560797130","https://openalex.org/W1586104099","https://openalex.org/W2097333193","https://openalex.org/W2107695330","https://openalex.org/W2123318312","https://openalex.org/W2129734311","https://openalex.org/W2133564696","https://openalex.org/W2135873687","https://openalex.org/W2148708890","https://openalex.org/W2155512447","https://openalex.org/W2186890008","https://openalex.org/W2513660799","https://openalex.org/W2591659448","https://openalex.org/W2741788241","https://openalex.org/W2773493195","https://openalex.org/W2807130468","https://openalex.org/W2963919854","https://openalex.org/W2964308564","https://openalex.org/W3201817155"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2057384730","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404"],"abstract_inverted_index":{"We":[0,14,46,152],"describe":[1],"Vicomtech's":[2],"participation":[3],"in":[4,40,61,95,147,163],"the":[5,22,66,69,80,90,113,141,148,164],"WMT":[6],"2018":[7],"Shared":[8],"Task":[9],"on":[10,50,89,108,140],"parallel":[11,58,117],"corpus":[12,70,149],"filtering.":[13],"aimed":[15],"to":[16,21],"evaluate":[17],"a":[18,86,102],"simple":[19,158],"approach":[20,49,131],"task,":[23,72],"which":[24,73],"can":[25,33],"efficiently":[26],"process":[27],"large":[28,144],"volumes":[29,76],"of":[30,68,77,92,115,126,143],"data":[31,104],"and":[32,44,54,136,159],"be":[34],"easily":[35],"deployed":[36],"for":[37,57],"new":[38],"datasets":[39,145],"different":[41],"language":[42],"pairs":[43,119],"domains.":[45],"based":[47,88,107],"our":[48],"STACC,":[51],"an":[52],"efficient":[53,139],"portable":[55,160],"method":[56,82,106],"sentence":[59,96,110,118],"identification":[60],"comparable":[62],"corpora.":[63],"To":[64],"address":[65],"specifics":[67],"filtering":[71,150],"features":[74],"significant":[75,124],"noisy":[78],"data,":[79],"core":[81],"was":[83],"expanded":[84],"with":[85,101,112,156],"penalty":[87],"amount":[91],"unknown":[93],"words":[94],"pairs.":[97],"Additionally,":[98],"we":[99],"experimented":[100],"complementary":[103],"saturation":[105],"source":[109],"n-grams,":[111],"goal":[114],"demoting":[116],"that":[120],"do":[121],"not":[122],"contribute":[123],"amounts":[125],"yet":[127],"unobserved":[128],"n-grams.":[129],"Our":[130],"requires":[132],"no":[133],"prior":[134],"training":[135],"is":[137],"highly":[138],"type":[142],"featured":[146],"task.":[151],"achieved":[153],"competitive":[154],"results":[155],"this":[157],"method,":[161],"ranking":[162],"top":[165],"half":[166],"among":[167],"competing":[168],"systems":[169],"overall.":[170]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}