{"id":"https://openalex.org/W2143473969","doi":"https://doi.org/10.1142/s1793840608001834","title":"English-Chinese Transliteration Word Pair Extraction from Parallel Corpora","display_name":"English-Chinese Transliteration Word Pair Extraction from Parallel Corpora","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2143473969","doi":"https://doi.org/10.1142/s1793840608001834","mag":"2143473969"},"language":"en","primary_location":{"id":"doi:10.1142/s1793840608001834","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793840608001834","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","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/A5074625562","display_name":"Chengguo Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"CHENGGUO JIN","raw_affiliation_strings":["Department of Graduate School for Information Technology, PIRL 323, Pohang University of Science and Technology, San 31, Hyoja-dong, Nam-gu, Pohang, 790-784, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Graduate School for Information Technology, PIRL 323, Pohang University of Science and Technology, San 31, Hyoja-dong, Nam-gu, Pohang, 790-784, Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066848156","display_name":"Seung\u2010Hoon Na","orcid":"https://orcid.org/0000-0002-4372-7125"},"institutions":[{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SEUNG-HOON NA","raw_affiliation_strings":["Division of Electrical and Computer Engineering, POSTECH, Korea"],"affiliations":[{"raw_affiliation_string":"Division of Electrical and Computer Engineering, POSTECH, Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747075","display_name":"Dongil Kim","orcid":"https://orcid.org/0000-0001-7425-7579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DONG-IL KIM","raw_affiliation_strings":["Language Engineering Institute, YUST, China"],"affiliations":[{"raw_affiliation_string":"Language Engineering Institute, YUST, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101532821","display_name":"Jong-Hyeok Lee","orcid":"https://orcid.org/0000-0002-9584-856X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JONG-HYEOK LEE","raw_affiliation_strings":["Division of Electrical and Computer Engineering, POSTECH, Korea"],"affiliations":[{"raw_affiliation_string":"Division of Electrical and Computer Engineering, POSTECH, Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074625562"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11155707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"02","first_page":"169","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T12353","display_name":"Lexicography and Language Studies","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9290247559547424},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.9078882932662964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7399716377258301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7251830101013184},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.610081672668457},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5980554223060608},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.5495386123657227},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.48195526003837585},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2887803912162781},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11979052424430847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9290247559547424},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.9078882932662964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7399716377258301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7251830101013184},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.610081672668457},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5980554223060608},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.5495386123657227},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.48195526003837585},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2887803912162781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11979052424430847},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s1793840608001834","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793840608001834","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/39462","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/39462","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W128271544","https://openalex.org/W1983824829","https://openalex.org/W1984403654","https://openalex.org/W2122789960","https://openalex.org/W2127361019","https://openalex.org/W2913739034","https://openalex.org/W4246975491"],"related_works":["https://openalex.org/W72691019","https://openalex.org/W4298129735","https://openalex.org/W2352873965","https://openalex.org/W6244059","https://openalex.org/W2610615972","https://openalex.org/W3143538182","https://openalex.org/W2405494806","https://openalex.org/W2146853049","https://openalex.org/W4206274156","https://openalex.org/W637364"],"abstract_inverted_index":{"Bilingual":[0],"dictionary":[1],"construction":[2],"is":[3],"a":[4,52,63],"time-consuming":[5],"job;":[6],"therefore":[7],"many":[8],"studies":[9],"have":[10],"recently":[11],"focused":[12],"on":[13,35],"automatically":[14],"constructing":[15],"bilingual":[16,19],"dictionaries":[17],"from":[18,46],"texts.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"two":[26],"novel":[27],"approaches":[28,50,70],"called":[29],"dynamic":[30],"window":[31],"and":[32],"tokenizer":[33],"based":[34],"statistical":[36],"machine":[37],"transliteration":[38,44],"model":[39],"to":[40,75],"efficiently":[41],"extract":[42],"English-Chinese":[43],"pairs":[45],"parallel":[47],"corpora.":[48],"Our":[49],"achieve":[51],"significant":[53],"improvement":[54],"over":[55],"previous":[56],"methods":[57],"without":[58],"using":[59],"resources":[60],"such":[61],"as":[62],"Chinese":[64],"segmentor,":[65],"pronunciation":[66],"dictionaries;":[67],"hence":[68],"these":[69],"can":[71],"be":[72],"readily":[73],"applied":[74],"other":[76],"language":[77],"pairs.":[78]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
