{"id":"https://openalex.org/W2100240599","doi":"https://doi.org/10.1002/asi.10261","title":"Automatic construction of English/Chinese parallel corpora","display_name":"Automatic construction of English/Chinese parallel corpora","publication_year":2003,"publication_date":"2003-04-16","ids":{"openalex":"https://openalex.org/W2100240599","doi":"https://doi.org/10.1002/asi.10261","mag":"2100240599"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.10261","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5086292931","display_name":"Christopher C. Yang","orcid":"https://orcid.org/0000-0001-5463-6926"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Christopher C. Yang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong Shatin, New\u00a0Territories, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong Shatin, New\u00a0Territories, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072945755","display_name":"Kar Wing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kar Wing Li","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong Shatin, New\u00a0Territories, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong Shatin, New\u00a0Territories, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.329,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":68,"citation_normalized_percentile":{"value":0.964435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"54","issue":"8","first_page":"730","last_page":"742"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997,"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":0.9997,"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":0.9983,"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/T10759","display_name":"Translation Studies and Practices","score":0.996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.51432836},{"id":"https://openalex.org/keywords/cross-language-information-retrieval","display_name":"Cross-language information retrieval","score":0.4746816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88152933},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.762394},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.63018274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62748027},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.51432836},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47662246},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.4746816},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44079247},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43613392},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36343086},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24726605},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.10261","pdf_url":null,"source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":59,"referenced_works":["https://openalex.org/W1510951099","https://openalex.org/W1521867232","https://openalex.org/W1540222736","https://openalex.org/W1543107604","https://openalex.org/W1554769004","https://openalex.org/W1557431580","https://openalex.org/W157432847","https://openalex.org/W1589814219","https://openalex.org/W1636405317","https://openalex.org/W1772262084","https://openalex.org/W1811404221","https://openalex.org/W1969178697","https://openalex.org/W1973923101","https://openalex.org/W1980156541","https://openalex.org/W1991305145","https://openalex.org/W1994790623","https://openalex.org/W2002919652","https://openalex.org/W2004821259","https://openalex.org/W2016221228","https://openalex.org/W2016630033","https://openalex.org/W2017180565","https://openalex.org/W2024181699","https://openalex.org/W2024797550","https://openalex.org/W2028770325","https://openalex.org/W2044013384","https://openalex.org/W2045634921","https://openalex.org/W2047959359","https://openalex.org/W2051885765","https://openalex.org/W2060234482","https://openalex.org/W2073078154","https://openalex.org/W2094969452","https://openalex.org/W2097333193","https://openalex.org/W2105678628","https://openalex.org/W2117331532","https://openalex.org/W2117652747","https://openalex.org/W2122141987","https://openalex.org/W2129287413","https://openalex.org/W2141325213","https://openalex.org/W2141658339","https://openalex.org/W2145080939","https://openalex.org/W2145386458","https://openalex.org/W2154384676","https://openalex.org/W2422872931","https://openalex.org/W2500014740","https://openalex.org/W2500773672","https://openalex.org/W2752885492","https://openalex.org/W2785456784","https://openalex.org/W2791996832","https://openalex.org/W2963010813","https://openalex.org/W3148327847","https://openalex.org/W3217208882","https://openalex.org/W354027070","https://openalex.org/W39478293","https://openalex.org/W4234196574","https://openalex.org/W4240563355","https://openalex.org/W4243013071","https://openalex.org/W47218471","https://openalex.org/W55052068","https://openalex.org/W587771840"],"related_works":["https://openalex.org/W4307459710","https://openalex.org/W4298129735","https://openalex.org/W3175595715","https://openalex.org/W3155572818","https://openalex.org/W2990400634","https://openalex.org/W2986030184","https://openalex.org/W2797913374","https://openalex.org/W2786253471","https://openalex.org/W2604275745","https://openalex.org/W2104907655"],"abstract_inverted_index":{"Abstract":[0],"As":[1,206],"the":[2,31,40,45,79,92,138,149,169,197,223,240,250,253,257,263,269,275,280,305,310],"demand":[3],"for":[4,17,70,209],"global":[5],"information":[6,21,111],"increases":[7],"significantly,":[8],"multilingual":[9,68],"corpora":[10,102,117],"has":[11],"become":[12],"a":[13,84,210],"valuable":[14],"linguistic":[15],"resource":[16],"applications":[18],"to":[19,29,60,90,142,167,195,229,238,248,301],"cross\u2010lingual":[20,110],"retrieval":[22],"and":[23,54,109,124,172,185,287,309],"natural":[24],"language":[25,93,211],"processing.":[26],"In":[27,153],"order":[28],"cross":[30,91],"boundaries":[32],"that":[33,103],"exist":[34],"between":[35,118],"different":[36],"languages,":[37,120],"dictionaries":[38,65],"are":[39,96,104,116,298],"most":[41,198],"typical":[42],"tools.":[43],"However,":[44],"general\u2010purpose":[46],"dictionary":[47],"is":[48,57,132,141,159,162,193,227,235,277,282,307,312],"less":[49],"sensitive":[50],"in":[51,106,220],"both":[52],"genre":[53],"domain.":[55],"It":[56],"also":[58,299],"impractical":[59],"manually":[61],"construct":[62,143],"tailored":[63],"bilingual":[64],"or":[66,100,216],"sophisticated":[67],"thesauri":[69],"large":[71],"applications.":[72],"Corpus\u2010based":[73],"approaches,":[74],"which":[75,89,161],"do":[76],"not":[77],"have":[78,245],"limitation":[80],"of":[81,114,137,202,252,274],"dictionaries,":[82],"provide":[83],"statistical":[85],"translation":[86,108,201],"model":[87],"with":[88],"boundary.":[94],"There":[95],"many":[97],"domain\u2010specific":[98],"parallel":[99,145],"comparable":[101],"employed":[105],"machine":[107],"retrieval.":[112],"Most":[113],"these":[115],"Indo\u2010European":[119],"such":[121],"as":[122,268],"English/French":[123],"English/Spanish.":[125],"The":[126,135,176,188,272,284],"Asian/Indo\u2010European":[127],"corpus,":[128,131],"especially":[129],"English/Chinese":[130,144],"relatively":[133],"sparse.":[134],"objective":[136],"present":[139],"research":[140],"corpus":[146],"automatically":[147],"from":[148],"World":[150],"Wide":[151],"Web.":[152],"this":[154],"paper,":[155],"an":[156,203],"alignment":[157,179],"method":[158,177,255],"presented":[160],"based":[163],"on":[164],"dynamic":[165],"programming":[166],"identify":[168],"one\u2010to\u2010one":[170],"Chinese":[171,200],"English":[173,204],"title":[174,181,242],"pairs.":[175,243],"includes":[178],"at":[180],"level,":[182],"word":[183,208],"level":[184],"character":[186],"level.":[187],"longest":[189],"common":[190],"subsequence":[191],"(LCS)":[192],"applied":[194],"find":[196],"reliable":[199],"word.":[205],"one":[207],"may":[212],"translate":[213],"into":[214],"two":[215],"more":[217],"words":[218],"repetitively":[219],"another":[221],"language,":[222],"edit":[224],"operation,":[225],"deletion,":[226],"used":[228,300],"resolve":[230],"redundancy.":[231],"A":[232],"score":[233],"function":[234],"then":[236],"proposed":[237,254],"determine":[239],"optimal":[241],"Experiments":[244],"been":[246],"conducted":[247],"investigate":[249],"performance":[251],"using":[256],"daily":[258],"press":[259],"release":[260,285],"articles":[261,286],"by":[262,291],"Hong":[264],"Kong":[265],"SAR":[266],"government":[267],"test":[270,302],"bed.":[271],"precision":[273,306],"result":[276],"0.998":[278],"while":[279],"recall":[281,311],"0.806.":[283],"speech":[288],"articles,":[289],"published":[290],"Hongkong":[292],"&":[293],"Shanghai":[294],"Banking":[295],"Corporation":[296],"Limited,":[297],"our":[303],"method,":[304],"1.00,":[308],"0.948.":[313]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2100240599","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2024-12-12T22:00:52.393786","created_date":"2016-06-24"}