{"id":"https://openalex.org/W2143134347","doi":null,"title":"Morphology-Aware Statistical Machine Translation Based on Morphs Induced in an Unsupervised Manner","display_name":"Morphology-Aware Statistical Machine Translation Based on Morphs Induced in an Unsupervised Manner","publication_year":2007,"publication_date":"2007-09-10","ids":{"openalex":"https://openalex.org/W2143134347","mag":"2143134347"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.6579","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.6579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.hut.fi/svirpioj/papers/virpioja07mtsummit.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003986900","display_name":"S\u00e1mi Virpioja","orcid":"https://orcid.org/0000-0002-3568-150X","observed_orcids":["https://orcid.org/0000-0002-3568-150X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e1mi Virpioja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050352884","display_name":"Jaakko J. V\u00e4yrynen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaakko V\u00e4yrynen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061159001","display_name":"Mathias Creutz","orcid":"https://orcid.org/0000-0003-1862-4172","observed_orcids":["https://orcid.org/0000-0003-1862-4172"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathias Creutz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1862-4172","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019927002","display_name":"Markus Sadeniemi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Markus Sadeniemi","raw_affiliation_strings":["Aalto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3087,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.97987039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/morfessor","display_name":"Morfessor","score":0.9290000200271606},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.8679999709129333},{"id":"https://openalex.org/keywords/subword-units","display_name":"subword units","score":0.9419999718666077},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.7170000076293945},{"id":"https://openalex.org/keywords/compounding","display_name":"compounding","score":0.6349999904632568},{"id":"https://openalex.org/keywords/inflection","display_name":"inflection","score":0.6589999794960022},{"id":"https://openalex.org/keywords/nordic-languages","display_name":"Scandinavian languages","score":0.7009999752044678}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7435153126716614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6965208649635315},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6908437013626099},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6835919618606567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822275519371033},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6687778234481812},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.6648600101470947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5855541229248047},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4187484383583069},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3067188858985901},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.6579","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.6579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.hut.fi/svirpioj/papers/virpioja07mtsummit.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.6647","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.6647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/MTS-2007-Virpioja.pdf","raw_type":"text"},{"id":"mag:2143134347","doi":null,"is_oa":false,"landing_page_url":"http://research.ics.aalto.fi/publications/svirpioj/virpioja07mtsummit.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W4629839","https://openalex.org/W22168010","https://openalex.org/W201532657","https://openalex.org/W1481546552","https://openalex.org/W1631260214","https://openalex.org/W2006969979","https://openalex.org/W2017802499","https://openalex.org/W2042783153","https://openalex.org/W2053306448","https://openalex.org/W2069712814","https://openalex.org/W2101105183","https://openalex.org/W2101711363","https://openalex.org/W2113788796","https://openalex.org/W2116614861","https://openalex.org/W2124807415","https://openalex.org/W2132248251","https://openalex.org/W2144523916","https://openalex.org/W2153653739","https://openalex.org/W2156700117","https://openalex.org/W2158195707","https://openalex.org/W2164529863","https://openalex.org/W2170464899","https://openalex.org/W2403096031","https://openalex.org/W2552556052"],"related_works":["https://openalex.org/W2153274722","https://openalex.org/W2152249239","https://openalex.org/W7098418402","https://openalex.org/W2166086342","https://openalex.org/W2251723370","https://openalex.org/W7096531889","https://openalex.org/W2741026152","https://openalex.org/W7095171641","https://openalex.org/W4242105955","https://openalex.org/W1605282883"],"abstract_inverted_index":{"In":[0,20,48],"this":[1,50],"paper,":[2],"we":[3,146],"apply":[4],"a":[5,12,33],"method":[6],"of":[7,30,94,113,135,138,182],"unsupervised":[8],"morphology":[9],"learning":[10],"to":[11,37,67,79,90,101],"state-of-the-art":[13],"phrase-based":[14],"statistical":[15,81],"machine":[16],"translation":[17],"(SMT)":[18],"system.":[19],"SMT,":[21],"words":[22,183],"are":[23,56,107,128,177],"traditionally":[24],"used":[25,89],"as":[26,72,171],"the":[27,45,76,92,95,99,131,136,139,154,159,164,180],"smallest":[28],"units":[29,83],"translation.":[31],"Such":[32],"system":[34],"generalizes":[35],"poorly":[36],"word":[38],"forms":[39],"that":[40,55,86,127],"do":[41],"not":[42,148],"occur":[43],"in":[44,130,143],"training":[46],"data.":[47],"particular,":[49],"is":[51,66,117,186],"problematic":[52],"for":[53,153,158],"languages":[54,122],"highly":[57,59],"compounding,":[58],"inflecting,":[60],"or":[61],"both.":[62],"An":[63],"alternative":[64],"way":[65],"use":[68,75],"sub-word":[69],"units,":[70],"such":[71],"morphemes.":[73],"We":[74],"Morfessor":[77],"algorithm":[78],"find":[80],"morphemelike":[82],"(called":[84],"morphs)":[85],"can":[87],"be":[88],"reduce":[91],"size":[93],"lexicon":[96],"and":[97,104,125,179],"improve":[98],"ability":[100],"generalize.":[102],"Translation":[103],"language":[105],"models":[106],"trained":[108],"directly":[109],"on":[110,119],"morphs":[111],"instead":[112],"words.":[114],"The":[115],"approach":[116],"tested":[118],"three":[120],"Nordic":[121],"(Danish,":[123],"Finnish,":[124],"Swedish)":[126],"included":[129],"Europarl":[132],"corpus":[133],"consisting":[134],"Proceedings":[137],"European":[140],"Parliament.":[141],"However,":[142],"our":[144],"experiments":[145],"did":[147],"obtain":[149],"higher":[150],"BLEU":[151],"scores":[152],"morph":[155],"model":[156],"than":[157],"standard":[160],"word-based":[161],"approach.":[162],"Nonetheless,":[163],"proposed":[165],"morph-based":[166],"solution":[167],"has":[168],"clear":[169],"benefits,":[170],"morphologically":[172],"well":[173],"motivated":[174],"structures":[175],"(phrases)":[176],"learned,":[178],"proportion":[181],"left":[184],"untranslated":[185],"clearly":[187],"reduced.":[188],"1.":[189]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}