{"id":"https://openalex.org/W2158061377","doi":"https://doi.org/10.1145/2556195.2556228","title":"Chinese-English mixed text normalization","display_name":"Chinese-English mixed text normalization","publication_year":2014,"publication_date":"2014-02-18","ids":{"openalex":"https://openalex.org/W2158061377","doi":"https://doi.org/10.1145/2556195.2556228","mag":"2158061377"},"language":"en","primary_location":{"id":"doi:10.1145/2556195.2556228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","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/A5100360407","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0947-4942"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444126","display_name":"Huan Chen","orcid":"https://orcid.org/0000-0003-2240-7381"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Chen","raw_affiliation_strings":["Fudan Univerisity, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan Univerisity, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100360407"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.045,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89700829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8805946111679077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.643891453742981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6152750253677368},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6127628087997437},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.6050137281417847},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5894491076469421},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.44309934973716736},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4226987063884735},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41541916131973267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20116877555847168},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15467891097068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805946111679077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.643891453742981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6152750253677368},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6127628087997437},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.6050137281417847},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5894491076469421},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.44309934973716736},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4226987063884735},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41541916131973267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20116877555847168},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15467891097068787},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2556195.2556228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W157541337","https://openalex.org/W168104989","https://openalex.org/W1260894361","https://openalex.org/W1630959083","https://openalex.org/W1693107767","https://openalex.org/W1777711742","https://openalex.org/W1894695003","https://openalex.org/W1924133215","https://openalex.org/W2005311637","https://openalex.org/W2016443085","https://openalex.org/W2028904519","https://openalex.org/W2036421848","https://openalex.org/W2053966956","https://openalex.org/W2056354103","https://openalex.org/W2096557605","https://openalex.org/W2097162496","https://openalex.org/W2117130368","https://openalex.org/W2127358574","https://openalex.org/W2133280805","https://openalex.org/W2135337869","https://openalex.org/W2135598948","https://openalex.org/W2137229991","https://openalex.org/W2138738738","https://openalex.org/W2142523187","https://openalex.org/W2146867136","https://openalex.org/W2152374779","https://openalex.org/W2153848201","https://openalex.org/W2156985047","https://openalex.org/W2160637503","https://openalex.org/W2162095731","https://openalex.org/W2163375626","https://openalex.org/W2163915185","https://openalex.org/W2163942301","https://openalex.org/W2164019165","https://openalex.org/W2170233894","https://openalex.org/W2172112754","https://openalex.org/W2250790341","https://openalex.org/W2251797717","https://openalex.org/W2405154930","https://openalex.org/W2406430107","https://openalex.org/W2799915114"],"related_works":["https://openalex.org/W2053241453","https://openalex.org/W2017590198","https://openalex.org/W2275433313","https://openalex.org/W2978974359","https://openalex.org/W2728430307","https://openalex.org/W2153980712","https://openalex.org/W2036556872","https://openalex.org/W2087532526","https://openalex.org/W1805578373","https://openalex.org/W2148276612"],"abstract_inverted_index":{"Along":[0],"with":[1,199],"the":[2,20,57,86,99,114,139,155,186,189,203,207,211,217],"expansion":[3],"of":[4,22,36,56,81,101,104,142,188],"globalization,":[5],"multilingualism":[6],"has":[7],"become":[8],"a":[9,23,126,146,170,180],"popular":[10],"social":[11,46],"phenomenon.":[12],"More":[13],"than":[14],"one":[15],"language":[16,60,152,197],"may":[17],"occur":[18],"in":[19,31,44,108,226],"context":[21],"single":[24],"conversation.":[25],"This":[26],"phenomenon":[27],"is":[28,80],"also":[29,193],"prevalent":[30],"China.":[32],"A":[33],"huge":[34],"variety":[35],"informal":[37,52,161],"Chinese":[38,105,109],"texts":[39,71,88],"contain":[40],"English":[41,107],"words,":[42],"especially":[43],"emails,":[45],"media,":[47],"and":[48,106,163,200],"other":[49,91,223],"user":[50,148],"generated":[51],"contents.":[53],"Since":[54],"most":[55],"existing":[58],"natural":[59,196],"processing":[61,66,227],"algorithms":[62],"were":[63],"designed":[64],"for":[65,118],"monolingual":[67],"information,":[68],"mixed":[69,87,102,120,228],"multilingual":[70],"cannot":[72],"be":[73],"well":[74],"analyzed":[75],"by":[76],"them.":[77,176],"Hence,":[78],"it":[79],"critical":[82],"importance":[83],"to":[84,124,130,168,174],"preprocess":[85],"before":[89],"applying":[90],"tasks.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,112,144,166,213],"firstly":[97],"analyze":[98],"phenomena":[100],"usage":[103],"microblogs.":[110],"Then,":[111],"detail":[113],"proposed":[115,190,204,218],"two-stage":[116],"method":[117,173,205,219],"normalizing":[119],"texts.":[121],"We":[122,192],"propose":[123,167],"use":[125,169],"noisy":[127],"channel":[128],"approach":[129],"translate":[131],"in-vocabulary":[132],"words":[133,157],"into":[134],"Chinese.":[135],"For":[136,154],"better":[137],"incorporating":[138],"historical":[140],"information":[141],"users,":[143],"introduce":[145],"novel":[147],"aware":[149],"neural":[150],"network":[151],"model.":[153],"out-of-vocabulary":[156],"(such":[158],"as":[159,206],"pronunciations,":[160],"expressions":[162],"et":[164],"al.),":[165],"graph-based":[171],"unsupervised":[172],"categorize":[175],"Experimental":[177],"results":[178],"on":[179],"manually":[181],"annotated":[182],"microblog":[183],"dataset":[184],"demonstrate":[185],"effectiveness":[187],"method.":[191],"evaluate":[194],"three":[195],"parsers":[198],"without":[201],"using":[202],"preprocessing":[208],"step.":[209],"From":[210],"results,":[212],"can":[214,220],"see":[215],"that":[216],"significantly":[221],"benefit":[222],"NLP":[224],"tasks":[225],"text.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}