{"id":"https://openalex.org/W76754543","doi":null,"title":"Unsupervised Statistical Segmentation of Japanese Kanji Strings","display_name":"Unsupervised Statistical Segmentation of Japanese Kanji Strings","publication_year":1999,"publication_date":"1999-07-01","ids":{"openalex":"https://openalex.org/W76754543","mag":"76754543"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.1026","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.1026","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/segmenttr.ps","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W76754543"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1813/7410","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rie Kubota Ando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lillian Lee","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4770-1712","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9887,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75806593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9984999895095825,"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":0.9984999895095825,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00019999999494757503,"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":0.8809999823570251},{"id":"https://openalex.org/keywords/unsupervised-segmentation","display_name":"unsupervised segmentation","score":0.8489999771118164},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.7269999980926514},{"id":"https://openalex.org/keywords/error-metrics","display_name":"error metrics","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.7545458078384399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004647612571716},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5928770303726196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5700982809066772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5693333745002747},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3312910795211792},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.1026","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.1026","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/segmenttr.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.696","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.696","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/segmenttr.pdf","raw_type":"text"},{"id":"pmh:oai:ecommons.cornell.edu:1813/7410","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1813/7410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"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":"technical report"},{"id":"mag:76754543","doi":null,"is_oa":false,"landing_page_url":"http://ecommons.cornell.edu/bitstream/1813/7410/1/99-1756.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":{"id":"pmh:oai:ecommons.cornell.edu:1813/7410","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1813/7410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"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":"technical report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316044","display_name":"GE Foundation","ror":"https://ror.org/04s45z758"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W76754543.pdf","grobid_xml":"https://content.openalex.org/works/W76754543.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W23665312","https://openalex.org/W82047487","https://openalex.org/W123715776","https://openalex.org/W138393627","https://openalex.org/W177759513","https://openalex.org/W204603808","https://openalex.org/W1992696103","https://openalex.org/W1997644175","https://openalex.org/W2015201047","https://openalex.org/W2047541753","https://openalex.org/W2048179523","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/W2244930836"],"related_works":["https://openalex.org/W2420792277","https://openalex.org/W1998974009","https://openalex.org/W7098678406","https://openalex.org/W138393627","https://openalex.org/W2189366115","https://openalex.org/W2771450499","https://openalex.org/W2474646533","https://openalex.org/W2395662515","https://openalex.org/W1992696103","https://openalex.org/W1828495135"],"abstract_inverted_index":{"Word":[0],"segmentation":[1],"is":[2,12],"an":[3,39],"important":[4],"issue":[5],"in":[6],"Japanese":[7,11,27],"language":[8],"processing":[9],"because":[10],"written":[13],"without":[14],"space":[15],"delimiters":[16],"between":[17],"words.":[18],"We":[19],"propose":[20],"a":[21,54],"simple":[22],"dictionary-less":[23],"method":[24],"to":[25],"segment":[26],"kanji":[28],"sequences":[29],"into":[30],"words":[31],"based":[32],"solely":[33],"on":[34],"character":[35],"$n$-gram":[36],"counts":[37],"from":[38],"unannotated":[40],"corpus.":[41],"The":[42],"performance":[43],"was":[44],"often":[45],"better":[46],"than":[47],"that":[48],"of":[49,56],"rule-based":[50],"morphological":[51],"analyzers":[52],"over":[53],"variety":[55],"both":[57],"standard":[58],"and":[59],"novel":[60],"error":[61],"metrics.":[62]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}