{"id":"https://openalex.org/W1998974009","doi":"https://doi.org/10.1017/s1351324902002954","title":"Mostly-unsupervised statistical segmentation of Japanese kanji sequences","display_name":"Mostly-unsupervised statistical segmentation of Japanese kanji sequences","publication_year":2003,"publication_date":"2003-06-01","ids":{"openalex":"https://openalex.org/W1998974009","doi":"https://doi.org/10.1017/s1351324902002954","mag":"1998974009"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324902002954","doi":"https://doi.org/10.1017/s1351324902002954","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324902002954","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","poland-140","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/cs/0205009","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065472000","display_name":"Rie Kubota Ando","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"RIE KUBOTA ANDO","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598, USA e-mail:","IBM Thomas J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598, USA e-mail: [email\u00a0protected]#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598, USA e-mail:","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598, USA e-mail: [email\u00a0protected]#TAB#","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876084","display_name":"Lillian Lee","orcid":"https://orcid.org/0000-0003-4770-1712","observed_orcids":["https://orcid.org/0000-0003-4770-1712","https://orcid.org/0000-0001-6577-9068"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LILLIAN LEE","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY 14853-7501 USA e-mail:","Department of Computer Science, Cornell University, Ithaca, NY 14853-7501 USA e-mail: llee@cs.cornell.edu#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY 14853-7501 USA e-mail:","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY 14853-7501 USA e-mail: llee@cs.cornell.edu#TAB#","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1201,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.88168876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"127","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/japanese-word-segmentation","display_name":"Japanese word segmentation","score":0.9419999718666077},{"id":"https://openalex.org/keywords/statistical-segmentation","display_name":"statistical segmentation","score":0.6549999713897705},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.896099328994751},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.8220045566558838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6571210622787476},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6546629667282104},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6411070823669434},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.5849165916442871},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5772160887718201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.56470787525177},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.450457364320755},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41461899876594543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3760111927986145},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.22462567687034607},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0793384313583374},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1017/s1351324902002954","doi":"https://doi.org/10.1017/s1351324902002954","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324902002954","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","poland-140","vabb-shw"],"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:cs/0205009","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cs/0205009","pdf_url":"https://arxiv.org/pdf/cs/0205009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.7594","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.7594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/home/llee/papers/segmentjnle.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.1623","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.1623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/home/llee/papers/segmentjnle.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.cs/0205009","doi":"https://doi.org/10.48550/arxiv.cs/0205009","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.cs/0205009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:cs/0205009","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cs/0205009","pdf_url":"https://arxiv.org/pdf/cs/0205009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.699999988079071}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W23665312","https://openalex.org/W82047487","https://openalex.org/W123715776","https://openalex.org/W138393627","https://openalex.org/W144101457","https://openalex.org/W177759513","https://openalex.org/W186138571","https://openalex.org/W201917955","https://openalex.org/W204603808","https://openalex.org/W1558333962","https://openalex.org/W1583770177","https://openalex.org/W1586407478","https://openalex.org/W1593045043","https://openalex.org/W1911521811","https://openalex.org/W1979262500","https://openalex.org/W1980862600","https://openalex.org/W1992696103","https://openalex.org/W1997644175","https://openalex.org/W2008434289","https://openalex.org/W2015201047","https://openalex.org/W2047541753","https://openalex.org/W2048179523","https://openalex.org/W2099111195","https://openalex.org/W2101711363","https://openalex.org/W2105783022","https://openalex.org/W2110190189","https://openalex.org/W2121497944","https://openalex.org/W2129287413","https://openalex.org/W2142263282","https://openalex.org/W2153161205","https://openalex.org/W2158874082","https://openalex.org/W2160356260","https://openalex.org/W2164177007","https://openalex.org/W2217873082","https://openalex.org/W2244930836","https://openalex.org/W2420187884","https://openalex.org/W2430312675","https://openalex.org/W2518835881","https://openalex.org/W2996160789","https://openalex.org/W3043710305","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W2393940967","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W120168696"],"abstract_inverted_index":{"Given":[0],"the":[1,43,49,70,129],"lack":[2],"of":[3,84,91,131],"word":[4,9,51],"delimiters":[5],"in":[6,18],"written":[7],"Japanese,":[8],"segmentation":[10,24,118],"is":[11],"generally":[12],"considered":[13],"a":[14,29,57,89,109,132],"crucial":[15],"first":[16],"step":[17],"processing":[19],"Japanese":[20,23,114],"texts.":[21],"Typical":[22],"algorithms":[25],"rely":[26],"either":[27],"on":[28,35,74,128],"lexicon":[30],"and":[31,42,80,120],"syntactic":[32],"analysis":[33],"or":[34],"pre-segmented":[36],"data;":[37],"but":[38],"these":[39],"are":[40,46],"labor-intensive,":[41],"lexico-syntactic":[44],"techniques":[45],"vulnerable":[47],"to":[48,79,115],"unknown":[50],"problem.":[52],"In":[53],"contrast,":[54],"we":[55,107],"introduce":[56,121],"novel,":[58],"more":[59],"robust":[60],"statistical":[61,100],"method":[62],"utilizing":[63],"unsegmented":[64],"training":[65],"data.":[66],"Despite":[67],"its":[68],"simplicity,":[69],"algorithm":[71,95,101],"yields":[72],"performance":[73],"long":[75],"kanji":[76],"sequences":[77],"comparable":[78],"sometimes":[81],"surpassing":[82],"that":[83,135],"state-of-the-art":[85],"morphological":[86],"analyzers":[87],"over":[88],"variety":[90],"error":[92],"metrics.":[93],"The":[94],"also":[96],"outperforms":[97],"another":[98],"mostly-unsupervised":[99],"previously":[102],"proposed":[103],"for":[104,113,138],"Chinese.":[105],"Additionally,":[106],"present":[108],"two-level":[110],"annotation":[111],"scheme":[112],"incorporate":[116],"multiple":[117,139],"granularities,":[119],"two":[122],"novel":[123],"evaluation":[124],"metrics,":[125],"both":[126],"based":[127],"notion":[130],"compatible":[133],"bracket,":[134],"can":[136],"account":[137],"granularities":[140],"simultaneously.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}