{"id":"https://openalex.org/W2980449122","doi":"https://doi.org/10.3390/info10100317","title":"MiNgMatch\u2014A Fast N-gram Model for Word Segmentation of the Ainu Language","display_name":"MiNgMatch\u2014A Fast N-gram Model for Word Segmentation of the Ainu Language","publication_year":2019,"publication_date":"2019-10-16","ids":{"openalex":"https://openalex.org/W2980449122","doi":"https://doi.org/10.3390/info10100317","mag":"2980449122"},"language":"en","primary_location":{"id":"doi:10.3390/info10100317","doi":"https://doi.org/10.3390/info10100317","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info10100317","pdf_url":"https://www.mdpi.com/2078-2489/10/10/317/pdf?version=1571967074","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2980449122"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/10/10/317/pdf?version=1571967074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052162979","display_name":"Karol Nowakowski","orcid":"https://orcid.org/0000-0001-7435-4061","observed_orcids":["https://orcid.org/0000-0001-7435-4061"]},"institutions":[{"id":"https://openalex.org/I98957242","display_name":"Kitami Institute of Technology","ror":"https://ror.org/05wks2t16","country_code":"JP","type":"education","lineage":["https://openalex.org/I4405287286","https://openalex.org/I98957242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Karol Nowakowski","raw_affiliation_strings":["Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7435-4061","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan","institution_ids":["https://openalex.org/I98957242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015548774","display_name":"Michal E. Ptaszynski","orcid":"https://orcid.org/0000-0002-1910-9183","observed_orcids":["https://orcid.org/0000-0002-1910-9183"]},"institutions":[{"id":"https://openalex.org/I98957242","display_name":"Kitami Institute of Technology","ror":"https://ror.org/05wks2t16","country_code":"JP","type":"education","lineage":["https://openalex.org/I4405287286","https://openalex.org/I98957242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michal Ptaszynski","raw_affiliation_strings":["Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1910-9183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan","institution_ids":["https://openalex.org/I98957242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039659770","display_name":"Fumito Masui","orcid":"https://orcid.org/0000-0001-9979-8734","observed_orcids":["https://orcid.org/0000-0001-9979-8734"]},"institutions":[{"id":"https://openalex.org/I98957242","display_name":"Kitami Institute of Technology","ror":"https://ror.org/05wks2t16","country_code":"JP","type":"education","lineage":["https://openalex.org/I4405287286","https://openalex.org/I98957242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumito Masui","raw_affiliation_strings":["Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9979-8734","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kitami Institute of Technology, 165 Koen-cho, Kitami, Hokkaido 090-8507, Japan","institution_ids":["https://openalex.org/I98957242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5052162979"],"corresponding_institution_ids":["https://openalex.org/I98957242"],"apc_list":{"value":1000,"currency":"CHF","value_usd":1013},"apc_paid":{"value":1000,"currency":"CHF","value_usd":1013},"fwci":0.3005,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60228201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"10","issue":"10","first_page":"317","last_page":"317"},"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/T10028","display_name":"Topic Modeling","score":0.0003000000142492354,"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":0.00019999999494757503,"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/word-segmentation","display_name":"word segmentation","score":0.9929999709129333},{"id":"https://openalex.org/keywords/ainu-language","display_name":"Ainu language","score":0.8989999890327454},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.7889999747276306},{"id":"https://openalex.org/keywords/word-boundary-detection","display_name":"word boundary detection","score":0.796999990940094},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8539999723434448},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8360000252723694},{"id":"https://openalex.org/keywords/kneser-ney-smoothing","display_name":"Kneser-Ney smoothing","score":0.8169999718666077},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502184152603149},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7135723829269409},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6909587383270264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6380375027656555},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.637142539024353},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6225290298461914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580421507358551},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.47786587476730347},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46912360191345215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46830570697784424},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4608795940876007},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.43493491411209106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15771570801734924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07553049921989441},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/info10100317","doi":"https://doi.org/10.3390/info10100317","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info10100317","pdf_url":"https://www.mdpi.com/2078-2489/10/10/317/pdf?version=1571967074","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01268:0004631424","doi":null,"is_oa":true,"landing_page_url":"https://kitami-it.repo.nii.ac.jp/records/8938","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal article"},{"id":"pmh:oai:doaj.org/article:e42952efb4f0445ea940931bcaa49337","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/e42952efb4f0445ea940931bcaa49337","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 10, Iss 10, p 317 (2019)","raw_type":"article"},{"id":"pmh:oai:kitami-it.repo.nii.ac.jp:00008938","doi":null,"is_oa":true,"landing_page_url":"https://kitami-it.repo.nii.ac.jp/records/8938","pdf_url":null,"source":{"id":"https://openalex.org/S7407063273","display_name":"Kitami Institute of Technology Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.3390/info10100317","doi":"https://doi.org/10.3390/info10100317","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info10100317","pdf_url":"https://www.mdpi.com/2078-2489/10/10/317/pdf?version=1571967074","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","poland-40","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980449122.pdf","grobid_xml":"https://content.openalex.org/works/W2980449122.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W165283731","https://openalex.org/W204603808","https://openalex.org/W613335405","https://openalex.org/W625315570","https://openalex.org/W1934041838","https://openalex.org/W1979145089","https://openalex.org/W1992696103","https://openalex.org/W2036516910","https://openalex.org/W2080496921","https://openalex.org/W2097927681","https://openalex.org/W2109664771","https://openalex.org/W2123442489","https://openalex.org/W2127863960","https://openalex.org/W2129287413","https://openalex.org/W2163377725","https://openalex.org/W2217873082","https://openalex.org/W2233994034","https://openalex.org/W2250659129","https://openalex.org/W2251627854","https://openalex.org/W2251811146","https://openalex.org/W2252193936","https://openalex.org/W2252225757","https://openalex.org/W2508899723","https://openalex.org/W2740838408","https://openalex.org/W2804033347","https://openalex.org/W2896649846","https://openalex.org/W2902964203","https://openalex.org/W2950186769","https://openalex.org/W2952054097","https://openalex.org/W2962885853","https://openalex.org/W2963628345","https://openalex.org/W2963997155","https://openalex.org/W2964093505","https://openalex.org/W3115271704","https://openalex.org/W6640281019"],"related_works":["https://openalex.org/W2902964203","https://openalex.org/W1791508882","https://openalex.org/W7045928859","https://openalex.org/W3115738938","https://openalex.org/W2251364186","https://openalex.org/W2252193936","https://openalex.org/W190156351","https://openalex.org/W2369209412","https://openalex.org/W104489331","https://openalex.org/W2252010429"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,38,136],"is":[2],"an":[3],"essential":[4],"task":[5],"in":[6,66,83,93],"automatic":[7],"language":[8,87,114],"processing":[9],"for":[10],"languages":[11],"where":[12,21],"there":[13],"are":[14,25],"no":[15],"explicit":[16],"word":[17,37,46,135],"boundary":[18],"markers,":[19],"or":[20],"space-delimited":[22],"orthographic":[23],"words":[24],"too":[26],"coarse-grained.":[27],"In":[28,60],"this":[29],"paper":[30],"we":[31,74,99,144,167],"introduce":[32],"the":[33,42,50,57,84,89,147,155,170],"MiNgMatch":[34],"Segmenter\u2014a":[35],"fast":[36],"algorithm,":[39,152],"which":[40],"reduces":[41],"problem":[43],"of":[44,53,81,88,96,103,150],"identifying":[45],"boundaries":[47],"to":[48,62,176,182],"finding":[49],"shortest":[51],"sequence":[52,139],"lexical":[54,112],"n-grams":[55],"matching":[56],"input":[58],"text.":[59],"order":[61],"validate":[63],"our":[64,106,151],"method":[65],"a":[67,78,101,122,131],"low-resource":[68],"scenario":[69],"involving":[70],"extremely":[71],"sparse":[72],"data,":[73],"tested":[75],"it":[76],"with":[77,108,124,154],"small":[79],"corpus":[80],"text":[82],"critically":[85],"endangered":[86],"Ainu":[90],"people":[91],"living":[92],"northern":[94],"parts":[95],"Japan.":[97],"Furthermore,":[98],"performed":[100],"series":[102],"experiments":[104],"comparing":[105],"algorithm":[107],"systems":[109],"utilizing":[110],"state-of-the-art":[111],"n-gram-based":[113],"modelling":[115],"techniques":[116],"(namely,":[117],"Stupid":[118],"Backoff":[119],"model":[120,123,133],"and":[121,164,179],"modified":[125],"Kneser-Ney":[126],"smoothing),":[127],"as":[128,130,137,189],"well":[129],"neural":[132],"performing":[134],"character":[138],"labelling.":[140],"The":[141],"experimental":[142],"results":[143],"obtained":[145],"demonstrate":[146],"high":[148],"performance":[149],"comparable":[153],"other":[156,177,183],"best-performing":[157],"models.":[158],"Given":[159],"its":[160],"low":[161],"computational":[162],"cost":[163],"competitive":[165],"results,":[166],"believe":[168],"that":[169],"proposed":[171],"approach":[172],"could":[173],"be":[174],"extended":[175],"languages,":[178],"possibly":[180],"also":[181],"Natural":[184],"Language":[185],"Processing":[186],"tasks,":[187],"such":[188],"speech":[190],"recognition.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2019-10-25T00:00:00"}