{"id":"https://openalex.org/W4403487196","doi":"https://doi.org/10.3233/faia240952","title":"A Hybrid Approach towards Chinese Spelling and Splitting Error Correction","display_name":"A Hybrid Approach towards Chinese Spelling and Splitting Error Correction","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487196","doi":"https://doi.org/10.3233/faia240952"},"language":"en","primary_location":{"id":"doi:10.3233/faia240952","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240952","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240952","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240952","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101205416","display_name":"Junhong Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Liang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015809194","display_name":"Junnan Zhu","orcid":"https://orcid.org/0000-0002-9856-2946"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junnan Zhu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102830655","display_name":"Feifei Zhai","orcid":"https://orcid.org/0000-0002-9121-691X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Zhai","raw_affiliation_strings":["Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051932647","display_name":"Nanchang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanchang Cheng","raw_affiliation_strings":["National Broadcast Media Language Resources Monitoring and Research Center, Communication University of China, Beijing, China, liangjunhong2022@ia.ac.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Broadcast Media Language Resources Monitoring and Research Center, Communication University of China, Beijing, China, liangjunhong2022@ia.ac.cn","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101763829","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-4911-4717"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9003,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82086336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8737000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8737000226974487,"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/T14025","display_name":"Educational Technology and Assessment","score":0.868399977684021,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8428999781608582,"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/spelling","display_name":"Spelling","score":0.9199341535568237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5605075359344482},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5110622644424438},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3542506694793701},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3472995162010193},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3056882619857788},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2558956742286682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22411894798278809},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10560601949691772}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.9199341535568237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5605075359344482},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5110622644424438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3542506694793701},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3472995162010193},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3056882619857788},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2558956742286682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22411894798278809},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10560601949691772}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240952","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240952","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240952","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240952","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240952","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240952","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487196.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2021532426"],"abstract_inverted_index":{"Existing":[0],"Chinese":[1,28,48,61,98],"spelling":[2,133],"check":[3],"(CSC)":[4],"methods":[5],"have":[6],"limitations":[7],"in":[8,71],"correcting":[9],"variable-length":[10,56],"error":[11],"characters,":[12],"requiring":[13],"the":[14,20,44,60,125],"input":[15],"and":[16,32,54,67,73,96,118,134],"output":[17],"to":[18,50,77,114,123],"be":[19],"same":[21],"length.":[22],"They":[23],"mainly":[24],"focus":[25],"on":[26],"modelling":[27,147],"characters\u2019":[29],"phonetic":[30],"information":[31,146],"generating":[33],"candidates":[34],"for":[35,148],"each":[36],"position.":[37],"In":[38],"contrast,":[39],"few":[40],"approaches":[41],"delve":[42],"into":[43],"intricacies":[45],"of":[46],"splitting":[47,55,135],"characters":[49],"address":[51,78],"glyph":[52],"errors":[53],"corrections.":[57],"We":[58,81],"define":[59],"Splitting":[62],"Error":[63,86],"Correction":[64,87],"(CSEC)":[65],"task":[66],"develop":[68],"CSEC":[69],"datasets":[70],"news":[72],"social":[74],"media":[75],"domains":[76],"this":[79],"issue.":[80],"then":[82,101],"propose":[83],"Soft-Masked":[84],"Multi-feature":[85],"(SoMu)":[88],"model,":[89],"which":[90],"first":[91],"generates":[92],"semantic,":[93],"phonetic,":[94],"graphic,":[95],"unique":[97],"Wubi":[99],"embeddings,":[100],"integrates":[102],"those":[103],"features":[104],"through":[105],"selective":[106],"gating":[107],"fusion,":[108],"followed":[109],"by":[110],"a":[111],"soft-mask":[112],"strategy":[113],"filter":[115],"incorrect":[116],"tokens":[117],"finally":[119],"use":[120],"transformer":[121],"layers":[122],"predict":[124],"correct":[126],"ones.":[127],"This":[128],"model":[129,142],"effectively":[130],"addresses":[131],"both":[132],"errors.":[136],"Extensive":[137],"analysis":[138],"shows":[139],"that":[140],"our":[141],"significantly":[143],"improves":[144],"character-splitting":[145],"CSEC.":[149],"Our":[150],"dataset":[151],"is":[152],"available":[153],"at":[154],"https://github.com/Skywalker-Harrison/SoMu.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
