{"id":"https://openalex.org/W2506719862","doi":"https://doi.org/10.1145/2933396","title":"A Seed-Based Method for Generating Chinese Confusion Sets","display_name":"A Seed-Based Method for Generating Chinese Confusion Sets","publication_year":2016,"publication_date":"2016-07-22","ids":{"openalex":"https://openalex.org/W2506719862","doi":"https://doi.org/10.1145/2933396","mag":"2506719862"},"language":"en","primary_location":{"id":"doi:10.1145/2933396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2933396","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5100396217","display_name":"Liangliang Liu","orcid":"https://orcid.org/0000-0003-1189-7717"},"institutions":[{"id":"https://openalex.org/I905225518","display_name":"Shanghai University of International Business and Economics","ror":"https://ror.org/031t68441","country_code":"CN","type":"education","lineage":["https://openalex.org/I905225518"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangliang Liu","raw_affiliation_strings":["School of Business Information, Shanghai University of International Business and Economics, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business Information, Shanghai University of International Business and Economics, Shanghai, China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103295802","display_name":"Cungen Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cungen Cao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5486,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83836167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.995199978351593,"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/T13629","display_name":"Text Readability and Simplification","score":0.9922999739646912,"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/confusion","display_name":"Confusion","score":0.8591628670692444},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.739266574382782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6053215861320496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5658334493637085},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5592883825302124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5395627617835999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4756590723991394},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4503515958786011},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44430622458457947},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43592965602874756},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.4338659942150116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.281379759311676},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15862679481506348},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13891687989234924},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07395187020301819}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.8591628670692444},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.739266574382782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6053215861320496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5658334493637085},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5592883825302124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5395627617835999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756590723991394},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4503515958786011},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44430622458457947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43592965602874756},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.4338659942150116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.281379759311676},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15862679481506348},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13891687989234924},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07395187020301819},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2933396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2933396","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2466027935","display_name":null,"funder_award_id":"91224006 and 61173063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W130884385","https://openalex.org/W1542236488","https://openalex.org/W1579838312","https://openalex.org/W2016871293","https://openalex.org/W2034038326","https://openalex.org/W2102249999","https://openalex.org/W2110993209","https://openalex.org/W2118996379","https://openalex.org/W2119966617","https://openalex.org/W2129271949","https://openalex.org/W2158318493","https://openalex.org/W2271844496","https://openalex.org/W2349298628","https://openalex.org/W2367188249","https://openalex.org/W2388526155","https://openalex.org/W2834209825","https://openalex.org/W2877833389","https://openalex.org/W2928461459","https://openalex.org/W2949916273","https://openalex.org/W3008796173","https://openalex.org/W4254373586","https://openalex.org/W7011671179"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2964976023","https://openalex.org/W1982477181","https://openalex.org/W4366202965","https://openalex.org/W1969293528","https://openalex.org/W2349679704","https://openalex.org/W4389633859","https://openalex.org/W2570625548"],"abstract_inverted_index":{"In":[0,20,52,74,104,146],"natural":[1],"language,":[2],"people":[3],"often":[4],"misuse":[5],"a":[6,9,34,38,45,57,80,120,123,164,191],"word":[7,47,173],"(called":[8,17],"\u201cconfused":[10],"word\u201d)":[11],"in":[12,96,101,128,139,212],"place":[13],"of":[14,44,49,60,70,82,137,158,199,220],"other":[15],"words":[16],"\u201cconfusing":[18],"words\u201d).":[19],"misspelling":[21,29,214],"corrections,":[22],"many":[23],"approaches":[24],"to":[25,177,216],"finding":[26],"and":[27,113,133,182],"correcting":[28],"errors":[30],"are":[31,110,117,135],"based":[32,92],"on":[33,93],"simple":[35],"notion":[36],"called":[37,122],"\u201cconfusion":[39],"set.\u201d":[40],"The":[41],"confusion":[42,64,84,108,115,125,180,201,210],"set":[43],"confused":[46],"consists":[48],"confusing":[50,144,161],"words.":[51],"this":[53,105],"article,":[54],"we":[55,78,150,170,206],"propose":[56],"new":[58,179],"method":[59,67,198],"building":[61],"Chinese":[62,88,166,213],"character":[63,97,102],"sets.":[65],"Our":[66],"is":[68,91,203],"composed":[69],"two":[71],"major":[72],"phases.":[73],"the":[75,114,140,147,152,185,209,218],"first":[76],"phase,":[77,106,149],"build":[79],"list":[81],"seed":[83],"sets":[85,109,116,202,211],"for":[86],"each":[87],"character,":[89,143,160],"which":[90,129],"measuring":[94],"similarity":[95,100],"pinyin":[98],"or":[99],"shape.":[103],"all":[107],"constructed":[111],"manually,":[112],"organized":[118],"into":[119,190],"graph,":[121],"\u201cseed":[124],"graph\u201d":[126],"(SCG),":[127],"vertices":[130],"denote":[131],"characters":[132,138],"edges":[134],"pairs":[136,157,181,186],"form":[141],"(confused":[142,159],"character).":[145],"second":[148],"extend":[151],"SCG":[153],"by":[154],"acquiring":[155],"more":[156],"character)":[162],"from":[163],"large":[165],"corpus.":[167],"For":[168],"this,":[169],"use":[171,208],"several":[172],"patterns":[174],"(or":[175],"patterns)":[176],"generate":[178],"then":[183],"verify":[184],"before":[187],"adding":[188],"them":[189],"SCG.":[192],"Comprehensive":[193],"experiments":[194],"show":[195,217],"that":[196],"our":[197,221],"extending":[200],"effective.":[204],"Also,":[205],"shall":[207],"corrections":[215],"utility":[219],"method.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}