{"id":"https://openalex.org/W2030019187","doi":"https://doi.org/10.1145/1282080.1282081","title":"A phonetic similarity model for automatic extraction of transliteration pairs","display_name":"A phonetic similarity model for automatic extraction of transliteration pairs","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2030019187","doi":"https://doi.org/10.1145/1282080.1282081","mag":"2030019187"},"language":"en","primary_location":{"id":"doi:10.1145/1282080.1282081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1282080.1282081","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 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/A5027993773","display_name":"Jin\u2010Shea Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jin-Shea Kuo","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100831531","display_name":"Ying\u2010Kuei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Kuei Yang","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027993773"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":7.9788,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97229362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"2","first_page":"6","last_page":"6"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9918000102043152,"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/transliteration","display_name":"Transliteration","score":0.8334342241287231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8259794116020203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.806745171546936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6563119888305664},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6053742170333862},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.41324496269226074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3652990162372589}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8334342241287231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259794116020203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.806745171546936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6563119888305664},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6053742170333862},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.41324496269226074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3652990162372589},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1282080.1282081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1282080.1282081","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"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 Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W115924709","https://openalex.org/W125241024","https://openalex.org/W180782768","https://openalex.org/W182831726","https://openalex.org/W190082078","https://openalex.org/W1506212051","https://openalex.org/W1563762850","https://openalex.org/W1618885279","https://openalex.org/W1847185164","https://openalex.org/W1950854090","https://openalex.org/W1981202432","https://openalex.org/W1983824829","https://openalex.org/W1985500785","https://openalex.org/W1997538087","https://openalex.org/W2004955904","https://openalex.org/W2006426911","https://openalex.org/W2006969979","https://openalex.org/W2019614587","https://openalex.org/W2032571942","https://openalex.org/W2049633694","https://openalex.org/W2053705431","https://openalex.org/W2054579058","https://openalex.org/W2054648860","https://openalex.org/W2055543848","https://openalex.org/W2055910046","https://openalex.org/W2066636486","https://openalex.org/W2075241709","https://openalex.org/W2107854516","https://openalex.org/W2115513413","https://openalex.org/W2122789960","https://openalex.org/W2134534213","https://openalex.org/W2150028966","https://openalex.org/W2155330785","https://openalex.org/W2166749644","https://openalex.org/W2405494806","https://openalex.org/W2597684388","https://openalex.org/W2603454388","https://openalex.org/W2913739034","https://openalex.org/W2916009164","https://openalex.org/W4255511007"],"related_works":["https://openalex.org/W191669241","https://openalex.org/W2109468486","https://openalex.org/W2069398544","https://openalex.org/W2514064218","https://openalex.org/W2094188777","https://openalex.org/W2112609279","https://openalex.org/W2132658536","https://openalex.org/W1581825163","https://openalex.org/W2399404538","https://openalex.org/W2366310385"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"an":[3,102,151],"approach":[4,162],"for":[5],"the":[6,21,46,50,66,71,76,86,91,106,142,145,168,182],"automatic":[7,176],"extraction":[8,51,177],"of":[9,33,52,59,79,108,129,144,154,178],"transliteration":[10,23,53,74,92,114,179],"pairs":[11,54,180],"from":[12],"Chinese":[13,39],"Web":[14,183],"corpora.":[15],"In":[16],"this":[17],"approach,":[18],"we":[19,69,89],"formulate":[20,117],"machine":[22],"process":[24,58],"using":[25],"a":[26,38,56,80,96,130,135],"syllable-based":[27],"phonetic":[28,34,47,118,131,146],"similarity":[29,48,119,132,147],"model":[30,133,148],"which":[31],"consists":[32],"confusion":[35],"matrices":[36],"and":[37,126],"character":[40],"n":[41],"-gram":[42],"language":[43],"model.":[44],"With":[45],"model,":[49],"becomes":[55],"two-step":[57],"recognition":[60,67],"followed":[61],"by":[62,149],"validation:":[63],"First,":[64],"in":[65,75,85,112,156,181],"process,":[68,88],"identify":[70],"most":[72],"probable":[73],"k":[77],"-neighborhood":[78],"recognized":[81],"English":[82],"word.":[83],"Then,":[84],"validation":[87],"qualify":[90],"pair":[93],"candidates":[94],"with":[95],"hypothesis":[97],"test.":[98],"We":[99,121],"carry":[100],"out":[101],"analytical":[103],"study":[104],"on":[105,134],"statistics":[107],"several":[109],"key":[110],"factors":[111],"English-Chinese":[113],"to":[115,174],"help":[116],"modeling.":[120],"then":[122],"conduct":[123],"both":[124],"supervised":[125,157,169],"unsupervised":[127,160],"learning":[128,161],"development":[136],"database.":[137],"The":[138,159],"experimental":[139],"results":[140],"validate":[141],"effectiveness":[143],"achieving":[150],"F":[152],"-measure":[153],"0.739":[155],"learning.":[158],"works":[163],"almost":[164],"as":[165,167],"well":[166],"one,":[170],"thus":[171],"allowing":[172],"us":[173],"deploy":[175],"space.":[184]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}