{"id":"https://openalex.org/W2980605255","doi":"https://doi.org/10.1145/3358695.3360941","title":"Automatic Construction of Chinese Typo-Pairs Based on Web Corpus","display_name":"Automatic Construction of Chinese Typo-Pairs Based on Web Corpus","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980605255","doi":"https://doi.org/10.1145/3358695.3360941","mag":"2980605255"},"language":"en","primary_location":{"id":"doi:10.1145/3358695.3360941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358695.3360941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence - Companion Volume","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/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":true,"raw_author_name":"Liangliang Liu","raw_affiliation_strings":["School of Statistics and Information, Shanghai University of International Business and Economics, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics and Information, Shanghai University of International Business and Economics, China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036456471","display_name":"Xue Fu","orcid":"https://orcid.org/0000-0001-9518-4081"},"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":"Xue Fu","raw_affiliation_strings":["School of Statistics and Information, Shanghai University of International Business and Economics, China"],"affiliations":[{"raw_affiliation_string":"School of Statistics and Information, Shanghai University of International Business and Economics, China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602439","display_name":"Haibo Liu","orcid":"https://orcid.org/0000-0002-4213-2883"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Jiangsu University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Jiangsu University of Science and Technology, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035901540","display_name":"Xinyu Cao","orcid":"https://orcid.org/0000-0002-4403-9762"},"institutions":[{"id":"https://openalex.org/I4210146077","display_name":"China National Institute of Standardization","ror":"https://ror.org/03qzxj964","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146077"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Cao","raw_affiliation_strings":["China National Institute of Standardization, China"],"affiliations":[{"raw_affiliation_string":"China National Institute of Standardization, China","institution_ids":["https://openalex.org/I4210146077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103072509","display_name":"Haitao Wang","orcid":"https://orcid.org/0009-0000-3938-4759"},"institutions":[{"id":"https://openalex.org/I4210146077","display_name":"China National Institute of Standardization","ror":"https://ror.org/03qzxj964","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146077"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["China National Institute of Standardization, China"],"affiliations":[{"raw_affiliation_string":"China National Institute of Standardization, China","institution_ids":["https://openalex.org/I4210146077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100396217"],"corresponding_institution_ids":["https://openalex.org/I905225518"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12458783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9817000031471252,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9578999876976013,"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":0.6934490203857422},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4827572703361511},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4635452628135681},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4417889416217804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38233423233032227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934490203857422},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4827572703361511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4635452628135681},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4417889416217804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38233423233032227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3358695.3360941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358695.3360941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence - Companion Volume","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1985177845","https://openalex.org/W2010595692","https://openalex.org/W2018616927","https://openalex.org/W2357910663","https://openalex.org/W2506719862","https://openalex.org/W4236160123"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,6,29,74,80,95,153,169,173,182],"development":[2],"of":[3,8],"big":[4],"data,":[5],"amount":[7],"text":[9,38,46,113,148],"data":[10,43],"is":[11,33,91,133],"growing":[12],"bigger":[13,15],"and":[14,22,56,100,122,166,179],"in":[16,63,73,97,125,146,172],"which":[17,83,110,142],"errors":[18,47],"are":[19,119],"also":[20],"more":[21,61],"more.":[23],"The":[24,88],"traditional":[25],"human-correction":[26],"cannot":[27],"meet":[28],"actual":[30],"demand.":[31],"It":[32],"a":[34,64,159],"trend":[35],"for":[36],"automatic":[37,149],"proofing":[39],"by":[40,68],"using":[41,162,176],"computer":[42],"processing.":[44],"Chinese":[45,65,81,98,112,126,137,147],"can":[48,143],"be":[49,104,144],"divided":[50,105],"into":[51,106,158],"two":[52],"categories:":[53],"non-word":[54,101],"error":[55,102],"real-word":[57],"error.":[58],"One":[59],"or":[60],"character":[62,70],"word":[66,75,89],"replaced":[67],"other":[69],"will":[71,103],"result":[72],"does":[76],"not":[77],"belong":[78],"to":[79,135],"dictionary,":[82],"we":[84],"call":[85],"\"non-word":[86],"error\".":[87],"segmentation":[90],"firstly":[92],"performed":[93],"on":[94],"corpus":[96],"NLP,":[99],"several":[107,115],"disperse":[108],"strings,":[109],"bring":[111],"proofreading":[114,150],"problems,":[116],"because":[117],"there":[118],"single-character":[120],"words":[121,124,157,171],"multi-characters":[123],"dictionary.":[127],"In":[128],"this":[129],"paper,":[130],"an":[131],"approach":[132],"proposed":[134],"construct":[136],"typo-pairs":[138],"from":[139],"Web":[140],"corpus,":[141],"used":[145],"efficiently.":[151],"Firstly,":[152],"method":[154],"adds":[155],"similar":[156,170],"candidate":[160,174],"set":[161,175],"fuzzy":[163],"matching":[164],"algorithm,":[165],"then":[167],"validates":[168],"statistical":[177],"models,":[178],"finally":[180],"constructs":[181],"typo-pairs.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
