{"id":"https://openalex.org/W2139755556","doi":"https://doi.org/10.3115/1218955.1218979","title":"Finding ideographic representations of Japanese names written in Latin script via language identification and corpus validation","display_name":"Finding ideographic representations of Japanese names written in Latin script via language identification and corpus validation","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2139755556","doi":"https://doi.org/10.3115/1218955.1218979","mag":"2139755556"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1218979","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218979","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218979&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1218979&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102002603","display_name":"Yan Qu","orcid":"https://orcid.org/0000-0003-2967-9785"},"institutions":[{"id":"https://openalex.org/I4210155069","display_name":"Clairvoyant Technology (United States)","ror":"https://ror.org/04m281x40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155069"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Qu","raw_affiliation_strings":["Clairvoyance Corporation, Pittsburgh, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clairvoyance Corporation, Pittsburgh, PA#TAB#","institution_ids":["https://openalex.org/I4210155069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039513155","display_name":"Gregory Grefenstette","orcid":"https://orcid.org/0000-0001-8479-049X"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I4210097138","display_name":"CEA Paris-Saclay - Etablissement de Fontenay-aux-roses","ror":"https://ror.org/010j2gw05","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210097138","https://openalex.org/I4210128565"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gregory Grefenstette","raw_affiliation_strings":["LIC2M/LIST/CEA, Fontenay-aux-Roses, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIC2M/LIST/CEA, Fontenay-aux-Roses, France#TAB#","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861","https://openalex.org/I4210097138"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"es"},"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":0.992900013923645,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8445683121681213},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.7967302203178406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7624720931053162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6609312891960144},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5571594834327698},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5162898898124695},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5139274597167969},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.5099834203720093},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.49158820509910583},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4417807161808014},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39204517006874084},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14962127804756165},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.08627250790596008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445683121681213},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.7967302203178406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7624720931053162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6609312891960144},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5571594834327698},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5162898898124695},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5139274597167969},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.5099834203720093},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.49158820509910583},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4417807161808014},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39204517006874084},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14962127804756165},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.08627250790596008},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1218955.1218979","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218979","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218979&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1218955.1218979","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218979","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1218979&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139755556.pdf","grobid_xml":"https://content.openalex.org/works/W2139755556.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1485221229","https://openalex.org/W1533946607","https://openalex.org/W1591338396","https://openalex.org/W1997538087","https://openalex.org/W2090362702","https://openalex.org/W2115513413","https://openalex.org/W2117901289","https://openalex.org/W2189352381","https://openalex.org/W2913739034","https://openalex.org/W2952677840","https://openalex.org/W4234516903"],"related_works":["https://openalex.org/W3020951519","https://openalex.org/W3173084154","https://openalex.org/W2334448532","https://openalex.org/W2982021180","https://openalex.org/W2131563376","https://openalex.org/W2065474030","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2067508358","https://openalex.org/W2388604329"],"abstract_inverted_index":{"Multilingual":[0],"applications":[1,21],"frequently":[2],"involve":[3],"dealing":[4],"with":[5,132],"proper":[6],"names,":[7],"but":[8],"names":[9,141],"are":[10],"often":[11],"missing":[12],"in":[13,60],"bilingual":[14],"lexicons.":[15],"This":[16],"problem":[17],"is":[18,41],"exacerbated":[19],"for":[20,50,95,124],"involving":[22],"translation":[23],"between":[24],"Latin-scripted":[25],"languages":[26,29],"and":[27,34,75,119,142,151],"Asian":[28],"such":[30],"as":[31],"Chinese,":[32],"Japanese":[33,139],"Korean":[35],"(CJK)":[36],"where":[37],"simple":[38],"string":[39],"copying":[40],"not":[42],"a":[43,47,56,61,99,107,114,125],"solution.":[44],"We":[45,128],"present":[46],"novel":[48],"approach":[49,66,131],"generating":[51],"the":[52,70,73,78,90,122,130],"ideographic":[53],"representations":[54],"of":[55,72,93,109,116,138,149],"CJK":[57],"name":[58,79],"written":[59],"Latin":[62],"script.":[63],"The":[64],"proposed":[65],"involves":[67],"first":[68,105],"identifying":[69],"origin":[71],"name,":[74],"then":[76,112],"back-transliterating":[77],"to":[80],"all":[81],"possible":[82],"Chinese":[83],"characters":[84],"using":[85],"language-specific":[86],"mappings.":[87],"To":[88],"reduce":[89],"massive":[91],"number":[92],"possibilities":[94],"computation,":[96],"we":[97,144],"apply":[98],"three-tier":[100],"filtering":[101,104],"process":[102],"by":[103],"through":[106,113,121],"set":[108,115],"attested":[110,117],"bigrams,":[111],"terms,":[118],"lastly":[120],"WWW":[123],"final":[126],"validation.":[127],"illustrate":[129],"English-to-Japanese":[133],"back-transliteration.":[134],"Against":[135],"test":[136],"sets":[137],"given":[140],"surnames,":[143],"have":[145],"achieved":[146],"average":[147],"precisions":[148],"73%":[150],"90%,":[152],"respectively.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}