{"id":"https://openalex.org/W2146330116","doi":"https://doi.org/10.3115/1075096.1075157","title":"Morphological analysis of a large spontaneous speech corpus in Japanese","display_name":"Morphological analysis of a large spontaneous speech corpus in Japanese","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2146330116","doi":"https://doi.org/10.3115/1075096.1075157","mag":"2146330116"},"language":"en","primary_location":{"id":"doi:10.3115/1075096.1075157","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075157","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075157","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075157","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108358235","display_name":"Kiyotaka Uchimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115057","display_name":"Kyoto Research Park","ror":"https://ror.org/028807987","country_code":"JP","type":"archive","lineage":["https://openalex.org/I4210115057"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyotaka Uchimoto","raw_affiliation_strings":["Communications Research Laboratory, Kyoto, Japan","Communications Research Laboratory, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I4210115057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076532065","display_name":"Chikashi Nobata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115057","display_name":"Kyoto Research Park","ror":"https://ror.org/028807987","country_code":"JP","type":"archive","lineage":["https://openalex.org/I4210115057"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chikashi Nobata","raw_affiliation_strings":["Communications Research Laboratory, Kyoto, Japan","Communications Research Laboratory, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I4210115057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014198464","display_name":"Atsushi Yamada","orcid":"https://orcid.org/0000-0002-0887-0321"},"institutions":[{"id":"https://openalex.org/I4210115057","display_name":"Kyoto Research Park","ror":"https://ror.org/028807987","country_code":"JP","type":"archive","lineage":["https://openalex.org/I4210115057"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Yamada","raw_affiliation_strings":["Communications Research Laboratory, Kyoto, Japan","Communications Research Laboratory, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I4210115057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112502341","display_name":"Satoshi Sekine","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115057","display_name":"Kyoto Research Park","ror":"https://ror.org/028807987","country_code":"JP","type":"archive","lineage":["https://openalex.org/I4210115057"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Sekine","raw_affiliation_strings":["Communications Research Laboratory, Kyoto, Japan","Communications Research Laboratory, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Communications Research Laboratory, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I4210115057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058557768","display_name":"Hitoshi Isahara","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitoshi Isahara","raw_affiliation_strings":["New York University, New York, NY","New York Univ, New York, NY,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York Univ, New York, NY,","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8753,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88298261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"479","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8313148617744446},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7435276508331299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6875306367874146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6559651494026184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5742954611778259},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5137418508529663},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.5042601823806763},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11966708302497864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313148617744446},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7435276508331299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6875306367874146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6559651494026184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5742954611778259},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5137418508529663},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.5042601823806763},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11966708302497864},{"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:10.3115/1075096.1075157","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075157","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075157","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.6031","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.6031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/pdfs/Uchimoto.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.5280","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.5280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/pdf/Uchimoto.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2eb629b2-9aad-400b-a731-067e30f71a09","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/2eb629b2-9aad-400b-a731-067e30f71a09","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Uchimoto, K, Nobata, C, Yamada, A, Sekine, S & Isahara, H 2003, Morphological Analysis of a Large Spontaneous Speech Corpus in Japanese. in the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003).","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/1075096.1075157","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075157","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075157","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2146330116.pdf","grobid_xml":"https://content.openalex.org/works/W2146330116.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W56012926","https://openalex.org/W1238390741","https://openalex.org/W1515346963","https://openalex.org/W1529196404","https://openalex.org/W1997767101","https://openalex.org/W2032558547","https://openalex.org/W2061229922","https://openalex.org/W2096175520","https://openalex.org/W2125513361","https://openalex.org/W2135892731","https://openalex.org/W2143921245","https://openalex.org/W3025808629"],"related_works":["https://openalex.org/W1965453504","https://openalex.org/W2296205523","https://openalex.org/W2396342956","https://openalex.org/W2486838646","https://openalex.org/W3128305375","https://openalex.org/W2626026432","https://openalex.org/W2251183413","https://openalex.org/W2949108231","https://openalex.org/W2006539681","https://openalex.org/W2046224275"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2,20],"two":[3,33,107],"methods":[4,126],"for":[5,57,95,103],"detecting":[6,96],"word":[7,45,58,69,75],"segments":[8,59,70],"and":[9,19,60,64,97,101],"their":[10,61],"morphological":[11],"information":[12],"in":[13],"a":[14,24,89],"Japanese":[15],"spontaneous":[16,26],"speech":[17,27],"corpus,":[18],"how":[21],"to":[22,40],"tag":[23],"large":[25],"corpus":[28],"accurately":[29],"by":[30,83,123,128],"using":[31,84,124,129],"the":[32,106,113,131],"methods.":[34],"The":[35,47],"first":[36],"method":[37,49],"is":[38,50,121],"used":[39,51],"detect":[41],"any":[42],"type":[43,67,73],"of":[44,68,74,91,109],"segments.":[46,76],"second":[48],"when":[52,65],"there":[53],"are":[54],"several":[55],"definitions":[56],"POS":[62],"categories,":[63],"one":[66],"includes":[71],"another":[72],"In":[77],"this":[78],"paper,":[79],"we":[80,87],"show":[81,117],"that":[82,111,118],"semi-automatic":[85],"analysis":[86],"achieve":[88],"precision":[90],"better":[92,119],"than":[93,127],"99%":[94],"tagging":[98],"short":[99],"words":[100,110],"97%":[102],"long":[104],"words;":[105],"types":[108],"comprise":[112],"corpus.":[114],"We":[115],"also":[116],"accuracy":[120],"achieved":[122],"both":[125],"only":[130],"first.":[132]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}