{"id":"https://openalex.org/W2051490926","doi":"https://doi.org/10.1145/1165255.1165257","title":"Alignment of bilingual named entities in parallel corpora using statistical models and multiple knowledge sources","display_name":"Alignment of bilingual named entities in parallel corpora using statistical models and multiple knowledge sources","publication_year":2006,"publication_date":"2006-06-01","ids":{"openalex":"https://openalex.org/W2051490926","doi":"https://doi.org/10.1145/1165255.1165257","mag":"2051490926"},"language":"en","primary_location":{"id":"doi:10.1145/1165255.1165257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1165255.1165257","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/A5088029532","display_name":"Chun-Jen Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Jen Lee","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016135743","display_name":"Jason S. Chang","orcid":"https://orcid.org/0000-0002-8227-7382"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jason S. Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing R. Jang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088029532"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":3.53669115,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92874471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"2","first_page":"121","last_page":"145"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.996399998664856,"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":0.8972636461257935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.8032007813453674},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.7841856479644775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7275981307029724},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6787610650062561},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6509480476379395},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5502984523773193},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.5111413598060608},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4782508909702301},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42569828033447266},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12090644240379333},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08057281374931335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8972636461257935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.8032007813453674},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.7841856479644775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7275981307029724},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6787610650062561},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6509480476379395},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5502984523773193},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.5111413598060608},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4782508909702301},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42569828033447266},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12090644240379333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08057281374931335},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1165255.1165257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1165255.1165257","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W14030242","https://openalex.org/W35234968","https://openalex.org/W90066383","https://openalex.org/W187531367","https://openalex.org/W1491364644","https://openalex.org/W1505083828","https://openalex.org/W1520377376","https://openalex.org/W1538473846","https://openalex.org/W1595649706","https://openalex.org/W1973702599","https://openalex.org/W1983824829","https://openalex.org/W1984403654","https://openalex.org/W1991154713","https://openalex.org/W1991635536","https://openalex.org/W2004955904","https://openalex.org/W2006426911","https://openalex.org/W2006969979","https://openalex.org/W2010665722","https://openalex.org/W2014516359","https://openalex.org/W2024181699","https://openalex.org/W2024610712","https://openalex.org/W2027913861","https://openalex.org/W2036453285","https://openalex.org/W2047295649","https://openalex.org/W2056724340","https://openalex.org/W2066792529","https://openalex.org/W2094154703","https://openalex.org/W2100240599","https://openalex.org/W2120840702","https://openalex.org/W2122789960","https://openalex.org/W2123512824","https://openalex.org/W2129264959","https://openalex.org/W2134534213","https://openalex.org/W2137419020","https://openalex.org/W2138151602","https://openalex.org/W2144578941","https://openalex.org/W2150028966","https://openalex.org/W2156111839","https://openalex.org/W2156985047","https://openalex.org/W2165345215","https://openalex.org/W2168801328","https://openalex.org/W2483327705","https://openalex.org/W2574499132","https://openalex.org/W2612560781","https://openalex.org/W2787707806","https://openalex.org/W2913739034","https://openalex.org/W2955041689","https://openalex.org/W3021321775","https://openalex.org/W4239552663","https://openalex.org/W4250938570","https://openalex.org/W4299527668","https://openalex.org/W4365799834","https://openalex.org/W6635689572","https://openalex.org/W6703490699","https://openalex.org/W6731988637"],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W2384400852","https://openalex.org/W72691019","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2400846488","https://openalex.org/W4206274156"],"abstract_inverted_index":{"Named":[0],"entity":[1],"(NE)":[2],"extraction":[3],"is":[4,197],"one":[5],"of":[6,40,73,124,158,217],"the":[7,38,41,71,146,165,169,179,186,214],"fundamental":[8],"tasks":[9],"in":[10,28,55,155,204],"natural":[11],"language":[12],"processing":[13],"(NLP).":[14],"Although":[15],"many":[16],"studies":[17],"have":[18],"focused":[19],"on":[20,178],"identifying":[21],"NEs":[22,27,54,173],"within":[23],"monolingual":[24],"documents,":[25],"aligning":[26,52],"bilingual":[29,53,109,159],"documents":[30],"has":[31],"not":[32],"been":[33],"investigated":[34],"extensively":[35],"due":[36],"to":[37,51,151,161,207],"complexity":[39],"task.":[42],"In":[43,66],"this":[44],"article":[45],"we":[46,69],"introduce":[47],"a":[48,80,108,121,156],"new":[49],"approach":[50,216],"parallel":[56,113],"corpora":[57],"by":[58],"incorporating":[59],"statistical":[60,191],"models":[61,148,192],"with":[62,193],"multiple":[63],"knowledge":[64,132,195],"sources.":[65],"our":[67,208],"approach,":[68,188],"model":[70],"process":[72],"translating":[74],"an":[75],"English":[76],"NE":[77,154,167],"phrase":[78,101,110],"into":[79],"Chinese":[81,138],"equivalent":[82],"using":[83],"lexical":[84],"translation/transliteration":[85],"probabilities":[86,92],"for":[87,93],"word":[88,94,105],"translation":[89],"and":[90,103,112,115,141,163,171,200],"alignment":[91,102],"reordering.":[95],"The":[96,127],"method":[97,128],"involves":[98,130],"automatically":[99,116],"learning":[100],"acquiring":[104],"translations":[106],"from":[107,120],"dictionary":[111],"corpora,":[114],"discovering":[117],"transliteration":[118],"transformations":[119],"training":[122],"set":[123],"name-transliteration":[125],"pairs.":[126],"also":[129],"language-specific":[131],"functions,":[133],"including":[134],"handling":[135],"abbreviations,":[136],"recognizing":[137],"personal":[139],"names,":[140],"expanding":[142],"acronyms.":[143],"At":[144],"runtime,":[145],"proposed":[147,187],"are":[149,174],"applied":[150],"each":[152],"source":[153,170],"pair":[157],"sentences":[160],"generate":[162],"evaluate":[164],"target":[166,172],"candidates;":[168],"then":[175],"aligned":[176],"based":[177],"computed":[180],"probabilities.":[181],"Experimental":[182],"results":[183],"demonstrate":[184],"that":[185],"which":[189],"integrates":[190],"extra":[194],"sources,":[196],"highly":[198],"feasible":[199],"offers":[201],"significant":[202],"improvement":[203],"performance":[205],"compared":[206],"previous":[209],"work,":[210],"as":[211,213],"well":[212],"traditional":[215],"IBM":[218],"Model":[219],"4.":[220]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}