{"id":"https://openalex.org/W2294094610","doi":"https://doi.org/10.1162/coli_a_00243","title":"A Comparative Study of Minimally Supervised Morphological Segmentation","display_name":"A Comparative Study of Minimally Supervised Morphological Segmentation","publication_year":2016,"publication_date":"2016-02-23","ids":{"openalex":"https://openalex.org/W2294094610","doi":"https://doi.org/10.1162/coli_a_00243","mag":"2294094610"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00243","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00243","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00243","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063485128","display_name":"Teemu Ruokolainen","orcid":"https://orcid.org/0000-0001-7454-5300"},"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":true,"raw_author_name":"Teemu Ruokolainen","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086010432","display_name":"Oskar Kohonen","orcid":null},"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":"Oskar Kohonen","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035358986","display_name":"Kairit Sirts","orcid":"https://orcid.org/0000-0001-7388-2583"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Kairit Sirts","raw_affiliation_strings":["Tallinn University of Technology"],"affiliations":[{"raw_affiliation_string":"Tallinn University of Technology","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008922825","display_name":"Stig-Arne Gr\u00f6nroos","orcid":"https://orcid.org/0000-0002-3750-6924"},"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":"Stig-Arne Gr\u00f6nroos","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"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":"Mikko Kurimo","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"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/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":"Sami Virpioja","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063485128"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":7.5093,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97157342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"42","issue":"1","first_page":"91","last_page":"120"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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/discriminative-model","display_name":"Discriminative model","score":0.849542498588562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987738847732544},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7497014999389648},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.7097188830375671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6834955811500549},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6478540897369385},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5658390522003174},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49746397137641907},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4750535488128662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47299274802207947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41434842348098755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41134387254714966},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.41100236773490906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11195164918899536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09282693266868591}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.849542498588562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987738847732544},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7497014999389648},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.7097188830375671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6834955811500549},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6478540897369385},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5658390522003174},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49746397137641907},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4750535488128662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47299274802207947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41434842348098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41134387254714966},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41100236773490906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11195164918899536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09282693266868591},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00243","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00243","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00243","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/25369","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/3d6b53fb-2075-41cc-818b-5f8a705c0f71","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:doaj.org/article:dfa9140db60e4511b05a9977352a3f7c","is_oa":true,"landing_page_url":"https://doaj.org/article/dfa9140db60e4511b05a9977352a3f7c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 42, Iss 1 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00243","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00243","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00243","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4076502936","display_name":null,"funder_award_id":"2012-2017","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G4249896723","display_name":null,"funder_award_id":"251170","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322700","display_name":"Hariduse Infotehnoloogia Sihtasutus","ror":"https://ror.org/02e2avb86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2294094610.pdf","grobid_xml":"https://content.openalex.org/works/W2294094610.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W163104842","https://openalex.org/W309335912","https://openalex.org/W1511040277","https://openalex.org/W1570225887","https://openalex.org/W1582588624","https://openalex.org/W1584789643","https://openalex.org/W1616871572","https://openalex.org/W1650210997","https://openalex.org/W1905100302","https://openalex.org/W1952669422","https://openalex.org/W1969608442","https://openalex.org/W1975638594","https://openalex.org/W1983311927","https://openalex.org/W1987911237","https://openalex.org/W1990334093","https://openalex.org/W2008652694","https://openalex.org/W2032942114","https://openalex.org/W2047603832","https://openalex.org/W2053306448","https://openalex.org/W2069712814","https://openalex.org/W2070554026","https://openalex.org/W2074546930","https://openalex.org/W2097089247","https://openalex.org/W2097532276","https://openalex.org/W2100397666","https://openalex.org/W2102166778","https://openalex.org/W2111668269","https://openalex.org/W2117126688","https://openalex.org/W2117621558","https://openalex.org/W2120661206","https://openalex.org/W2126449874","https://openalex.org/W2126504272","https://openalex.org/W2129059886","https://openalex.org/W2130935327","https://openalex.org/W2134134392","https://openalex.org/W2138751265","https://openalex.org/W2141182089","https://openalex.org/W2142377809","https://openalex.org/W2147354085","https://openalex.org/W2147880316","https://openalex.org/W2150969560","https://openalex.org/W2152561112","https://openalex.org/W2153118244","https://openalex.org/W2158139315","https://openalex.org/W2163238067","https://openalex.org/W2164151151","https://openalex.org/W2168464035","https://openalex.org/W2169147927","https://openalex.org/W2170569305","https://openalex.org/W2179974023","https://openalex.org/W2250618788","https://openalex.org/W2251012068","https://openalex.org/W2251670681","https://openalex.org/W2252054421","https://openalex.org/W2295551984","https://openalex.org/W2296590378","https://openalex.org/W2502723504","https://openalex.org/W2917252841","https://openalex.org/W2952343510","https://openalex.org/W3183153947","https://openalex.org/W4210997624","https://openalex.org/W4251556668"],"related_works":["https://openalex.org/W4241414757","https://openalex.org/W4206127412","https://openalex.org/W4289013130","https://openalex.org/W4283366759","https://openalex.org/W2383186719","https://openalex.org/W3103292258","https://openalex.org/W2987280934","https://openalex.org/W2751624083","https://openalex.org/W3136209078","https://openalex.org/W2147102537"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,7,45,54,65,83],"comparative":[4],"study":[5],"of":[6,9,31,48,57,137],"subfield":[8],"morphology":[10],"learning":[11,38],"referred":[12],"to":[13,63],"as":[14],"minimally":[15,35],"supervised":[16,36],"morphological":[17,20],"segmentation.":[18],"In":[19,33,61],"segmentation,":[21],"word":[22,51,59],"forms":[23,30,52],"are":[24,42],"segmented":[25],"into":[26],"morphs,":[27],"the":[28,34,89,95,122,126,134,138,143],"surface":[29],"morphemes.":[32],"data-driven":[37],"setting,":[39],"segmentation":[40],"models":[41],"learned":[43],"from":[44],"small":[46],"number":[47],"manually":[49],"annotated":[50],"and":[53,106,125],"large":[55],"set":[56],"unannotated":[58],"forms.":[60],"addition":[62],"providing":[64],"literature":[66,90],"survey":[67],"on":[68,77,88,101,109],"published":[69],"methods,":[70],"we":[71,92],"present":[72],"an":[73],"in-depth":[74],"empirical":[75,127],"comparison":[76],"three":[78],"diverse":[79],"model":[80],"families,":[81],"including":[82],"detailed":[84],"error":[85],"analysis.":[86],"Based":[87],"survey,":[91],"conclude":[93],"that":[94,133],"existing":[96],"methodology":[97],"contains":[98],"substantial":[99],"work":[100,124],"generative":[102],"morph":[103],"lexicon-based":[104],"approaches":[105],"methods":[107],"based":[108],"discriminative":[110,144],"boundary":[111,145],"detection.":[112],"As":[113],"for":[114],"which":[115],"approach":[116],"has":[117],"been":[118],"more":[119],"successful,":[120],"both":[121],"previous":[123],"evaluation":[128],"presented":[129],"here":[130],"strongly":[131],"imply":[132],"current":[135],"state":[136],"art":[139],"is":[140],"yielded":[141],"by":[142],"detection":[146],"methodology.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
