{"id":"https://openalex.org/W2147686939","doi":"https://doi.org/10.3115/1220175.1220300","title":"A phonetic-based approach to Chinese chat text normalization","display_name":"A phonetic-based approach to Chinese chat text normalization","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2147686939","doi":"https://doi.org/10.3115/1220175.1220300","mag":"2147686939"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220300","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220300","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220300","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220300","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069555295","display_name":"Yunqing Xia","orcid":"https://orcid.org/0009-0005-8608-574X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yunqing Xia","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408983","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0002-7360-8864"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"993","last_page":"1000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976000189781189,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9972000122070312,"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":0.8721181154251099},{"id":"https://openalex.org/keywords/pinyin","display_name":"Pinyin","score":0.6766916513442993},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6729711294174194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6713108420372009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5358089208602905},{"id":"https://openalex.org/keywords/online-chat","display_name":"Online chat","score":0.48680540919303894},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4354536831378937},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4191315174102783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4069957137107849},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.21847668290138245},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20972120761871338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721181154251099},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.6766916513442993},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6729711294174194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6713108420372009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5358089208602905},{"id":"https://openalex.org/C2776849261","wikidata":"https://www.wikidata.org/wiki/Q287198","display_name":"Online chat","level":3,"score":0.48680540919303894},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4354536831378937},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4191315174102783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4069957137107849},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.21847668290138245},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20972120761871338},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1220175.1220300","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220300","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220300","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.4731","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.4731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1125.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.8834","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.8834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cst.cs.tsinghua.edu.cn/~xiayq/PDFs/COLACL06_yx.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/56069","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/56069","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220300","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220300","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220300","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147686939.pdf","grobid_xml":"https://content.openalex.org/works/W2147686939.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1601018556","https://openalex.org/W1604437366","https://openalex.org/W1784457082","https://openalex.org/W2097333193","https://openalex.org/W2134237567","https://openalex.org/W2355285064","https://openalex.org/W2757496889","https://openalex.org/W3088510249","https://openalex.org/W6605658417"],"related_works":["https://openalex.org/W2355589192","https://openalex.org/W2383579380","https://openalex.org/W2599785913","https://openalex.org/W2357614476","https://openalex.org/W2391413009","https://openalex.org/W2977960882","https://openalex.org/W3004865318","https://openalex.org/W2180791503","https://openalex.org/W3016183518","https://openalex.org/W1712848793"],"abstract_inverted_index":{"Chatting":[0],"is":[1,16,37,126],"a":[2],"popular":[3],"communication":[4],"media":[5],"on":[6],"the":[7,56,61,87,100,110,116],"Internet":[8],"via":[9,74],"ICQ,":[10],"chat":[11,44,52,69,104,133],"rooms,":[12],"etc.":[13],"Chat":[14],"language":[15,20,45,105,134],"different":[17],"from":[18,84,93],"natural":[19],"due":[21],"to":[22,65],"its":[23],"anomalous":[24],"and":[25,71,128],"dynamic":[26,35,57,103,132],"natures,":[27],"which":[28],"renders":[29],"conventional":[30],"NLP":[31],"tools":[32],"inapplicable.":[33],"The":[34],"problem":[36],"enormously":[38],"troublesome":[39],"because":[40],"it":[41],"makes":[42],"static":[43],"corpus":[46],"outdated":[47],"quickly":[48],"in":[49,80,130],"representing":[50],"contemporary":[51],"language.":[53],"To":[54,98],"address":[55],"problem,":[58],"we":[59,108],"propose":[60],"phonetic":[62,75,88,117],"mapping":[63,118],"models":[64],"present":[66],"mappings":[67,89],"between":[68],"terms":[70],"standard":[72,95],"words":[73],"transcription,":[76],"i.e.":[77],"Chinese":[78,96],"Pinyin":[79],"our":[81],"case.":[82],"Different":[83],"character":[85],"mappings,":[86],"can":[90],"be":[91],"constructed":[92],"available":[94],"corpus.":[97],"perform":[99],"task":[101],"of":[102],"term":[106],"normalization,":[107],"extend":[109],"source":[111],"channel":[112],"model":[113],"by":[114],"incorporating":[115],"models.":[119],"Experimental":[120],"results":[121],"show":[122],"that":[123],"this":[124],"method":[125],"effective":[127],"stable":[129],"normalizing":[131],"terms.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
