{"id":"https://openalex.org/W2252204808","doi":"https://doi.org/10.18653/v1/w15-3021","title":"Morphological Segmentation and OPUS for Finnish-English Machine Translation","display_name":"Morphological Segmentation and OPUS for Finnish-English Machine Translation","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252204808","doi":"https://doi.org/10.18653/v1/w15-3021","mag":"2252204808"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3021","pdf_url":"https://aclanthology.org/W15-3021.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 Tenth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W15-3021.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082417280","display_name":"J\u00f6rg Tiedemann","orcid":"https://orcid.org/0000-0003-3065-7989"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Tiedemann","raw_affiliation_strings":["Uppsala University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019929457","display_name":"Filip Ginter","orcid":"https://orcid.org/0000-0002-5484-6103"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Filip Ginter","raw_affiliation_strings":["University of Turku"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Turku","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048932608","display_name":"Jenna Kanerva","orcid":"https://orcid.org/0000-0003-4580-5366"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jenna Kanerva","raw_affiliation_strings":["University of Turku"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Turku","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"183"},"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":0.9991000294685364,"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":0.9916999936103821,"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/machine-translation","display_name":"Machine translation","score":0.7782468795776367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390865683555603},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6546028256416321},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.638981819152832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5869652032852173},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5855189561843872},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5672430992126465},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.563499927520752},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5107660293579102},{"id":"https://openalex.org/keywords/opus","display_name":"Opus","score":0.5071516036987305},{"id":"https://openalex.org/keywords/machine-translation-system","display_name":"Machine translation system","score":0.4860897362232208},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09744378924369812}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7782468795776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390865683555603},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6546028256416321},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.638981819152832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869652032852173},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5855189561843872},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5672430992126465},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.563499927520752},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5107660293579102},{"id":"https://openalex.org/C2778950570","wikidata":"https://www.wikidata.org/wiki/Q1466199","display_name":"Opus","level":2,"score":0.5071516036987305},{"id":"https://openalex.org/C2986258472","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation system","level":3,"score":0.4860897362232208},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09744378924369812},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-3021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3021","pdf_url":"https://aclanthology.org/W15-3021.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 Tenth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3021","pdf_url":"https://aclanthology.org/W15-3021.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 Tenth Workshop on Statistical Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252204808.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W102530743","https://openalex.org/W132913264","https://openalex.org/W160974077","https://openalex.org/W186995053","https://openalex.org/W338621447","https://openalex.org/W630532510","https://openalex.org/W1614298861","https://openalex.org/W1962622193","https://openalex.org/W1965299982","https://openalex.org/W2124807415","https://openalex.org/W2125768350","https://openalex.org/W2141440284","https://openalex.org/W2146574666","https://openalex.org/W2147838663","https://openalex.org/W2148708890","https://openalex.org/W2395418806"],"related_works":["https://openalex.org/W2890508380","https://openalex.org/W2985371315","https://openalex.org/W2917029047","https://openalex.org/W2061528982","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4391982595","https://openalex.org/W2963598809","https://openalex.org/W4388052519"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"baseline":[3],"systems":[4],"for":[5],"Finnish-English":[6],"and":[7,14,25,28,40,53],"English-Finnish":[8],"machine":[9],"translation":[10],"using":[11],"standard":[12],"phrasebased":[13],"factored":[15],"models":[16],"including":[17],"morphological":[18,26,58],"features.":[19],"We":[20],"experiment":[21],"with":[22],"compound":[23],"splitting":[24],"segmentation":[27],"study":[29],"the":[30,38,41,48,55],"effect":[31],"of":[32,50,57,60],"adding":[33],"noisy":[34],"out-of-domain":[35],"data":[36,52],"to":[37],"parallel":[39],"monolingual":[42],"training":[43,51],"data.":[44],"Our":[45],"results":[46],"stress":[47],"importance":[49],"demonstrate":[54],"effectiveness":[56],"pre-processing":[59],"Finnish.":[61]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
