{"id":"https://openalex.org/W2086889779","doi":"https://doi.org/10.1109/isuc.2008.82","title":"Compilation of the Balanced Corpus of Contemporary Written Japanese in the KOTONOHA Initiative (Invited Paper)","display_name":"Compilation of the Balanced Corpus of Contemporary Written Japanese in the KOTONOHA Initiative (Invited Paper)","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2086889779","doi":"https://doi.org/10.1109/isuc.2008.82","mag":"2086889779"},"language":"en","primary_location":{"id":"doi:10.1109/isuc.2008.82","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isuc.2008.82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Second International Symposium on Universal Communication","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5037501207","display_name":"Kikuo Maekawa","orcid":"https://orcid.org/0000-0001-6343-7689"},"institutions":[{"id":"https://openalex.org/I4210117430","display_name":"National Institute for Japanese Language and Linguistics","ror":"https://ror.org/02caqc891","country_code":"JP","type":"other","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210117430","https://openalex.org/I4210148627"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kikuo Maekawa","raw_affiliation_strings":["Department Language Research, The National Institute for Japanese Language, Japan","Dept. Language Res., Nat. Inst. for Japanese Language, Japan"],"affiliations":[{"raw_affiliation_string":"Department Language Research, The National Institute for Japanese Language, Japan","institution_ids":["https://openalex.org/I4210117430"]},{"raw_affiliation_string":"Dept. Language Res., Nat. Inst. for Japanese Language, Japan","institution_ids":["https://openalex.org/I4210117430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037501207"],"corresponding_institution_ids":["https://openalex.org/I4210117430"],"apc_list":null,"apc_paid":null,"fwci":4.5764,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94434849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.722000002861023,"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":0.722000002861023,"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/newspaper","display_name":"Newspaper","score":0.824225127696991},{"id":"https://openalex.org/keywords/british-national-corpus","display_name":"British National Corpus","score":0.5483293533325195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5361385941505432},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5340259075164795},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5198893547058105},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5034393668174744},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.467048317193985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44871360063552856},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43564102053642273},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.35096776485443115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.321346253156662},{"id":"https://openalex.org/keywords/media-studies","display_name":"Media studies","score":0.16451504826545715},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.10019418597221375}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.824225127696991},{"id":"https://openalex.org/C2776725116","wikidata":"https://www.wikidata.org/wiki/Q236935","display_name":"British National Corpus","level":2,"score":0.5483293533325195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5361385941505432},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5340259075164795},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5198893547058105},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5034393668174744},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.467048317193985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44871360063552856},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43564102053642273},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.35096776485443115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321346253156662},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.16451504826545715},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.10019418597221375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isuc.2008.82","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isuc.2008.82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Second International Symposium on Universal Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2760780548","https://openalex.org/W6744723507"],"related_works":["https://openalex.org/W2794113965","https://openalex.org/W300344534","https://openalex.org/W4388119661","https://openalex.org/W1587508994","https://openalex.org/W4380575491","https://openalex.org/W2907907821","https://openalex.org/W2077152605","https://openalex.org/W4315484253","https://openalex.org/W2237015346","https://openalex.org/W1967937307"],"abstract_inverted_index":{"Compilation":[0],"of":[1,11,30,39,45,56,65,79,86,99,102,111,127],"a":[2,28],"hundred":[3],"million":[4],"word":[5],"balanced":[6],"corpus":[7,26,70,118],"named":[8],"Balanced":[9],"Corpus":[10],"Contemporary":[12],"Written":[13],"Japanese":[14,23,41],"(BCCWJ)":[15],"is":[16,27],"underway":[17],"at":[18],"the":[19,31,36,43,46,51,57,66,69,83,92,96,100,124],"National":[20],"Institute":[21],"for":[22],"Language.":[24],"This":[25],"component":[29],"KOTONOHA":[32],"super-corpus":[33],"that":[34,61],"covers":[35],"full":[37],"range":[38],"modern":[40],"from":[42,74],"middle":[44],"19th":[47],"century":[48],"up":[49],"to":[50],"present.":[52],"The":[53,117],"unique":[54],"characteristics":[55],"BCCWJ":[58],"consists":[59,81,98],"in":[60,68,82,105,123],"about":[62],"two":[63,75],"third":[64],"samples":[67],"were":[71],"randomly":[72],"selected":[73],"statistical":[76],"populations:":[77],"one":[78],"them":[80],"publication":[84],"data":[85],"books,":[87],"magazines,":[88],"and":[89,95],"newspapers":[90],"during":[91],"years":[93],"2001-2005,":[94],"other":[97],"set":[101],"books":[103],"registered":[104],"more":[106],"than":[107],"13":[108],"public":[109],"libraries":[110],"Tokyo":[112],"metropolis":[113],"(335,000":[114],"different":[115],"books).":[116],"will":[119],"be":[120],"publicly":[121],"available":[122],"first":[125],"half":[126],"2011.":[128]},"counts_by_year":[{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}