{"id":"https://openalex.org/W2970999217","doi":"https://doi.org/10.18653/v1/w19-5432","title":"The University of Helsinki Submissions to the WMT19 Similar Language Translation Task","display_name":"The University of Helsinki Submissions to the WMT19 Similar Language Translation Task","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970999217","doi":"https://doi.org/10.18653/v1/w19-5432","mag":"2970999217"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5432","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w19-5432","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063672760","display_name":"Yves Scherrer","orcid":"https://orcid.org/0000-0001-5247-5073"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yves Scherrer","raw_affiliation_strings":["University of Helsinki"],"affiliations":[{"raw_affiliation_string":"University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047023030","display_name":"Ra\u00fal V\u00e1zquez","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ra\u00fal V\u00e1zquez","raw_affiliation_strings":["University of Helsinki"],"affiliations":[{"raw_affiliation_string":"University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003986900","display_name":"S\u00e1mi Virpioja","orcid":"https://orcid.org/0000-0002-3568-150X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sami Virpioja","raw_affiliation_strings":["University of Helsinki"],"affiliations":[{"raw_affiliation_string":"University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063672760"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6688044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"244"},"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":0.9997000098228455,"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":0.9923999905586243,"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/cognate","display_name":"Cognate","score":0.9082220792770386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893930673599243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7307777404785156},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7154707908630371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6721753478050232},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6682872772216797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6446700096130371},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.6249055862426758},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5858433842658997},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5857027173042297},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.49970221519470215},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.48040536046028137},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.43555590510368347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35068196058273315},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3276200294494629},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07476809620857239},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06408339738845825}],"concepts":[{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.9082220792770386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893930673599243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7307777404785156},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7154707908630371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6721753478050232},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6682872772216797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6446700096130371},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.6249055862426758},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5858433842658997},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5857027173042297},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.49970221519470215},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.48040536046028137},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.43555590510368347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35068196058273315},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3276200294494629},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07476809620857239},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06408339738845825},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w19-5432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5432","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"},{"id":"pmh:oai:helda.helsinki.fi:10138/305093","is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/W19-5432","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5432","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":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4459410915","display_name":"Found in Translation \u2013 Natural Language Understanding with Cross-Lingual Grounding","funder_award_id":"771113","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W214028658","https://openalex.org/W309335912","https://openalex.org/W1905100302","https://openalex.org/W1987408080","https://openalex.org/W2032942114","https://openalex.org/W2042783153","https://openalex.org/W2053306448","https://openalex.org/W2101105183","https://openalex.org/W2117621558","https://openalex.org/W2144600658","https://openalex.org/W2149327368","https://openalex.org/W2152561112","https://openalex.org/W2511950321","https://openalex.org/W2512848817","https://openalex.org/W2531207078","https://openalex.org/W2538358357","https://openalex.org/W2714176837","https://openalex.org/W2757141711","https://openalex.org/W2757281913","https://openalex.org/W2759409226","https://openalex.org/W2808154809","https://openalex.org/W2888893419","https://openalex.org/W2902827059","https://openalex.org/W2954254257","https://openalex.org/W2962732637","https://openalex.org/W2962784628","https://openalex.org/W2963212250","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963715460","https://openalex.org/W2963979492","https://openalex.org/W2964053711","https://openalex.org/W2977881703","https://openalex.org/W4249773576","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2356815520","https://openalex.org/W2360457743","https://openalex.org/W4379645529","https://openalex.org/W3009996856","https://openalex.org/W2974737450","https://openalex.org/W2367891843","https://openalex.org/W2369596954","https://openalex.org/W2561203018","https://openalex.org/W106971056","https://openalex.org/W1604851481"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,12,26,48,66,95],"University":[4],"of":[5,50,94],"Helsinki":[6],"Language":[7],"Technology":[8],"group's":[9],"participation":[10],"in":[11,45,114],"WMT":[13],"2019":[14],"similar":[15],"language":[16,27],"translation":[17,23,105],"task.":[18],"We":[19,74],"trained":[20],"neural":[21],"machine":[22],"models":[24,99],"for":[25,64,104],"pairs":[28],"Czech":[29],"textless-textgreater":[30,34],"Polish":[31],"and":[32,44,60,108,116],"Spanish":[33,107],"Portuguese.":[35],"Our":[36],"experiments":[37],"focused":[38],"on":[39,47],"different":[40,69],"subword":[41],"segmentation":[42,53,59,62,82],"methods,":[43,83],"particular":[46],"comparison":[49],"a":[51],"cognate-aware":[52,81],"method,":[54],"Cognate":[55],"Morfessor,":[56],"with":[57],"character":[58],"unsupervised":[61],"methods":[63],"which":[65],"data":[67],"from":[68,80],"languages":[70],"were":[71],"simply":[72],"concatenated.":[73],"did":[75],"not":[76],"observe":[77],"major":[78],"benefits":[79],"but":[84,110],"further":[85],"research":[86],"may":[87],"be":[88,102],"needed":[89],"to":[90,101],"explore":[91],"larger":[92],"parts":[93],"parameter":[96],"space.":[97],"Character-level":[98],"proved":[100],"competitive":[103],"between":[106],"Portuguese,":[109],"they":[111],"are":[112],"slower":[113],"training":[115],"decoding.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}