{"id":"https://openalex.org/W4306317008","doi":"https://doi.org/10.1145/3511808.3557636","title":"MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction","display_name":"MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317008","doi":"https://doi.org/10.1145/3511808.3557636"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557636","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557636","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113009131","display_name":"Wangjie Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangjie Jiang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015477867","display_name":"Zhihao Ye","orcid":"https://orcid.org/0009-0004-6045-2495"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Ye","raw_affiliation_strings":["Tencent Jarvis Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021091982","display_name":"Zijing Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijing Ou","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059804502","display_name":"Ruihui Zhao","orcid":"https://orcid.org/0000-0001-8070-5008"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihui Zhao","raw_affiliation_strings":["Tencent Jarvis Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068246417","display_name":"Jianguang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguang Zheng","raw_affiliation_strings":["Tencent Jarvis Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087964419","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-0811-6150"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Tencent Jarvis Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691219","display_name":"Bang Liu","orcid":"https://orcid.org/0000-0002-2272-6852"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bang Liu","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al Mila & CIFAR, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al Mila & CIFAR, Montreal, Canada","institution_ids":["https://openalex.org/I109736498","https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060359860","display_name":"Siheng Li","orcid":"https://orcid.org/0000-0003-1124-7474"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siheng Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020953714","display_name":"Yujiu Yang","orcid":"https://orcid.org/0000-0002-6427-1024"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiu Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051649145","display_name":"Yefeng Zheng","orcid":"https://orcid.org/0000-0003-2195-2847"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Tencent Jarvis Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5113009131"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0399,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78717541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4084","last_page":"4088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.9187244176864624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8295394778251648},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.726595938205719},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6090701222419739},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5363755226135254},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5178635120391846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5085428953170776},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4786480665206909},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47530850768089294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44985589385032654},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.081379234790802}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.9187244176864624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295394778251648},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.726595938205719},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6090701222419739},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5363755226135254},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5178635120391846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5085428953170776},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4786480665206909},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47530850768089294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44985589385032654},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.081379234790802},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557636","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557636","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557636","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557636","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317008.pdf","grobid_xml":"https://content.openalex.org/works/W4306317008.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494632860","https://openalex.org/W2131930823","https://openalex.org/W2163542005","https://openalex.org/W2251568283","https://openalex.org/W2251873470","https://openalex.org/W2296547479","https://openalex.org/W2531638282","https://openalex.org/W2564237127","https://openalex.org/W2601201959","https://openalex.org/W2892181857","https://openalex.org/W2892311186","https://openalex.org/W2892737606","https://openalex.org/W2952500220","https://openalex.org/W2983735660","https://openalex.org/W3034797320","https://openalex.org/W3035309733","https://openalex.org/W3173175058","https://openalex.org/W3173375787","https://openalex.org/W3173712076","https://openalex.org/W3173859131","https://openalex.org/W3174595604","https://openalex.org/W3176140329","https://openalex.org/W4221165114","https://openalex.org/W4238846128","https://openalex.org/W4255386139"],"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/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406","https://openalex.org/W2165071883"],"abstract_inverted_index":{"Chinese":[0,77],"Spelling":[1,78],"Correction":[2,79],"(CSC)":[3],"is":[4,50],"gaining":[5],"increasing":[6],"attention":[7],"in":[8,15,31,34,56,134,165],"recent":[9],"years.":[10],"Despite":[11],"its":[12,62],"extensive":[13,103],"use":[14],"many":[16],"applications,":[17],"such":[18],"as":[19],"search":[20],"engine":[21],"and":[22,37,81,136,150],"optical":[23],"character":[24],"recognition":[25],"system,":[26],"little":[27],"has":[28],"been":[29],"explored":[30],"medical":[32,39,48,105,118],"scenarios":[33],"which":[35],"complex":[36],"uncommon":[38],"entities":[40,49],"are":[41],"easily":[42],"misspelled.":[43],"Correcting":[44],"the":[45,57,73,130,148,155],"misspellings":[46],"of":[47,64,75,129],"arguably":[51],"more":[52],"difficult":[53],"than":[54],"those":[55],"open":[58],"domain":[59,66],"due":[60],"to":[61,95,157],"requirements":[63],"specific":[65,166],"knowledge.":[67],"In":[68,93],"this":[69],"work,":[70],"we":[71],"define":[72],"task":[74],"Medical-domain":[76],"(MCSC)":[80],"propose":[82],"MCSCSet,":[83],"a":[84,124],"large-scale":[85],"specialist-annotated":[86],"dataset":[87],"that":[88,161],"contains":[89],"about":[90],"200k":[91],"samples.":[92],"contrast":[94],"existing":[96],"open-domain":[97,149],"CSC":[98,164],"datasets,":[99],"MCSCSet":[100],"involves:":[101],"i)":[102],"real-world":[104],"queries":[106],"collected":[107],"from":[108],"Tencent":[109],"Yidian,":[110],"ii)":[111],"corresponding":[112,138],"misspelled":[113],"sentences":[114],"manually":[115],"annotated":[116],"by":[117],"specialists.":[119],"Our":[120],"work":[121,170],"further":[122],"offers":[123],"medical-domain":[125,151],"confusion":[126],"set":[127],"consisting":[128],"common":[131],"error-prone":[132],"characters":[133],"medicine":[135],"their":[137],"misspellings.":[139],"Extensive":[140],"empirical":[141],"studies":[142],"have":[143],"shown":[144],"significant":[145],"gaps":[146],"between":[147],"spelling":[152],"correction,":[153],"highlighting":[154],"need":[156],"develop":[158],"high-quality":[159],"datasets":[160],"allow":[162],"for":[163,177],"domains.":[167],"Moreover,":[168],"our":[169],"benchmarks":[171],"several":[172],"representative":[173],"methods,":[174],"establishing":[175],"baselines":[176],"future":[178],"work.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}