{"id":"https://openalex.org/W2034038326","doi":"https://doi.org/10.3115/1075218.1075250","title":"Automatic detecting/correcting errors in Chinese text by an approximate word-matching algorithm","display_name":"Automatic detecting/correcting errors in Chinese text by an approximate word-matching algorithm","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2034038326","doi":"https://doi.org/10.3115/1075218.1075250","mag":"2034038326"},"language":"en","primary_location":{"id":"doi:10.3115/1075218.1075250","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075250","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075250","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100434028","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0003-2343-084X"},"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":"Lei Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066941389","display_name":"Changning Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Changning Huang","raw_affiliation_strings":["Microsoft Research China, Beijing, China","Microsoft Research China, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research China, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research China, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701574","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-5701-1996"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research China, Beijing, China","Microsoft Research China, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research China, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research China, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102047158","display_name":"Haihua Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haihua Pan","raw_affiliation_strings":["City University of Hong Kong, Kowlong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowlong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100434028"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5127,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.75680972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"248","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9858999848365784,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7883039712905884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460613250732422},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7348284721374512},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.670755922794342},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6476378440856934},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5762770175933838},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5582157373428345},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5370411276817322},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5248018503189087},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5024800300598145},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4805079698562622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4288063049316406},{"id":"https://openalex.org/keywords/commentz-walter-algorithm","display_name":"Commentz-Walter algorithm","score":0.4270819127559662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4111669957637787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36818382143974304},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3483430743217468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15455350279808044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05601808428764343}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7883039712905884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460613250732422},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7348284721374512},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.670755922794342},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6476378440856934},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5762770175933838},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5582157373428345},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5370411276817322},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5248018503189087},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5024800300598145},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4805079698562622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4288063049316406},{"id":"https://openalex.org/C13052355","wikidata":"https://www.wikidata.org/wiki/Q5152399","display_name":"Commentz-Walter algorithm","level":4,"score":0.4270819127559662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4111669957637787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36818382143974304},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3483430743217468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15455350279808044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05601808428764343},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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:10.3115/1075218.1075250","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075250","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1075218.1075250","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075250","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075218.1075250","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2034038326.pdf","grobid_xml":"https://content.openalex.org/works/W2034038326.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1650656906","https://openalex.org/W2010595692"],"related_works":["https://openalex.org/W2257399947","https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W2141423589","https://openalex.org/W2378689532","https://openalex.org/W2245915510","https://openalex.org/W2502807948","https://openalex.org/W4398785990","https://openalex.org/W2386746909","https://openalex.org/W2359478580"],"abstract_inverted_index":{"An":[0],"approximate":[1],"word-matching":[2],"algorithm":[3],"for":[4],"Chinese":[5,16],"is":[6,22,33,64],"presented.":[7],"Based":[8],"on":[9],"this":[10],"algorithm,":[11],"an":[12],"effective":[13],"approach":[14],"to":[15],"spelling":[17,59],"error":[18,60],"detection":[19,61],"and":[20,49,62],"correction":[21,63],"implemented.":[23],"With":[24],"a":[25],"word":[26],"tri-gram":[27],"language":[28],"model,":[29],"the":[30,40,52,56],"optimal":[31,57],"string":[32],"searched":[34],"from":[35],"all":[36],"possible":[37],"derivation":[38],"of":[39,45],"input":[41],"sentence":[42,54],"using":[43],"operations":[44],"character":[46],"substitution,":[47],"insertion,":[48],"deletion.":[50],"Comparing":[51],"original":[53],"with":[55],"string,":[58],"realized":[65],"simultaneously.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}