{"id":"https://openalex.org/W2807746654","doi":"https://doi.org/10.1109/icsda.2017.8384473","title":"Corpus-based evaluation of Chinese text normalization","display_name":"Corpus-based evaluation of Chinese text normalization","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2807746654","doi":"https://doi.org/10.1109/icsda.2017.8384473","mag":"2807746654"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","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/A5100417561","display_name":"Sun\u2010Hee Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sunhee Kim","raw_affiliation_strings":["NAVER Corporation, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corporation, Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100417561"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80664376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9925000071525574,"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/T10759","display_name":"Translation Studies and Practices","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9686731100082397},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7999823093414307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7498673796653748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111796140670776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6180733442306519},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4832035303115845},{"id":"https://openalex.org/keywords/standard-chinese","display_name":"Standard Chinese","score":0.46141302585601807},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42663323879241943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4057881236076355},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35567042231559753}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9686731100082397},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7999823093414307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7498673796653748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111796140670776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6180733442306519},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4832035303115845},{"id":"https://openalex.org/C2776618157","wikidata":"https://www.wikidata.org/wiki/Q727694","display_name":"Standard Chinese","level":2,"score":0.46141302585601807},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42663323879241943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4057881236076355},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35567042231559753},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"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/icsda.2017.8384473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2103085228","https://openalex.org/W2160693947","https://openalex.org/W2164107060","https://openalex.org/W2293206651","https://openalex.org/W2404680331","https://openalex.org/W2591927543","https://openalex.org/W4295276571","https://openalex.org/W6696888824","https://openalex.org/W6713876942"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2368206661","https://openalex.org/W2012930958","https://openalex.org/W2884489049","https://openalex.org/W1668370815","https://openalex.org/W2139600619","https://openalex.org/W4300161491","https://openalex.org/W1972889872","https://openalex.org/W2181574814","https://openalex.org/W2358128423"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,71],"present":[4],"a":[5,9,20,57,73],"method":[6],"of":[7,12,15,31,45,59,95,105,108],"developing":[8],"corpus":[10,98],"consisting":[11],"various":[13],"categories":[14],"Non-Standard":[16],"Words":[17],"(NSWs)":[18],"and":[19,40,56,82],"representative":[21,74],"test":[22,75],"set":[23],"which":[24],"will":[25],"be":[26],"used":[27],"for":[28,37,52,66,79],"the":[29,32,53,92,96,102],"evaluation":[30],"text":[33],"normalization":[34],"modules":[35],"proposed":[36],"Standard":[38,54,80],"Mandarin":[39,55,81,84],"Taiwanese":[41,67,83],"Mandarin.":[42,68],"A":[43],"total":[44,58],"191,431":[46],"sentences":[47,61,78],"with":[48,62],"NSWs":[49,63],"are":[50,64,85],"extracted":[51,65],"731,524":[60],"In":[69],"order":[70],"make":[72],"set,":[76],"1,000":[77],"randomly":[86],"chosen":[87],"from":[88],"these":[89],"sentences,":[90],"maintaining":[91],"same":[93],"proportion":[94,104],"source":[97],"as":[99,101],"well":[100],"similar":[103],"each":[106],"category":[107],"NSWs.":[109]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}