{"id":"https://openalex.org/W2141569737","doi":"https://doi.org/10.1145/2407085.2407099","title":"An English-translated parallel corpus for the CJK Wikipedia collections","display_name":"An English-translated parallel corpus for the CJK Wikipedia collections","publication_year":2012,"publication_date":"2012-12-05","ids":{"openalex":"https://openalex.org/W2141569737","doi":"https://doi.org/10.1145/2407085.2407099","mag":"2141569737"},"language":"en","primary_location":{"id":"doi:10.1145/2407085.2407099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/57835/1/CJK2E-Wikipedia-XML-Corpus-V7.1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083079331","display_name":"Ling-Xiang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ling-Xiang Tang","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045420626","display_name":"Shlomo Geva","orcid":"https://orcid.org/0000-0003-1340-2802"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shlomo Geva","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050903724","display_name":"Andrew Trotman","orcid":"https://orcid.org/0000-0003-1253-7123"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrew Trotman","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083079331"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.8843,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80716065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"110"},"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8812886476516724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5931785106658936},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5625297427177429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5204418301582336},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.47158706188201904},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.47134682536125183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47117286920547485},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41637781262397766},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.15378087759017944},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.10376295447349548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812886476516724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5931785106658936},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5625297427177429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5204418301582336},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.47158706188201904},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.47134682536125183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47117286920547485},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41637781262397766},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.15378087759017944},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.10376295447349548}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2407085.2407099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:57835","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/57835/1/CJK2E-Wikipedia-XML-Corpus-V7.1.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.662.1480","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.662.1480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.qut.edu.au/57835/1/CJK2E-Wikipedia-XML-Corpus-V7.1.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:57835","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/57835/1/CJK2E-Wikipedia-XML-Corpus-V7.1.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141569737.pdf","grobid_xml":"https://content.openalex.org/works/W2141569737.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4879875","https://openalex.org/W33204889","https://openalex.org/W71491040","https://openalex.org/W1528364095","https://openalex.org/W2145424095","https://openalex.org/W2293072638","https://openalex.org/W2395569486","https://openalex.org/W2408639740","https://openalex.org/W2806438009","https://openalex.org/W2915344173","https://openalex.org/W2952244582","https://openalex.org/W6630826567"],"related_works":["https://openalex.org/W3123064333","https://openalex.org/W2143927888","https://openalex.org/W2242707303","https://openalex.org/W2757753881","https://openalex.org/W2123678043","https://openalex.org/W2125885330","https://openalex.org/W2902262852","https://openalex.org/W37319627","https://openalex.org/W1572297637","https://openalex.org/W2251265917"],"abstract_inverted_index":{"In":[0],"this":[1,50],"paper,":[2],"we":[3],"describe":[4],"a":[5],"machine-translated":[6],"parallel":[7],"English":[8,85],"corpus":[9,30,51],"for":[10,48,55],"the":[11,35,70,80,84],"NTCIR":[12],"Chinese,":[13],"Japanese":[14],"and":[15,40],"Korean":[16],"(CJK)":[17],"Wikipedia":[18,26,44],"collections.":[19],"This":[20],"document":[21],"collection":[22],"is":[23],"named":[24],"CJK2E":[25],"XML":[27],"corpus.":[28],"The":[29],"could":[31,52,74],"be":[32,53,75],"used":[33,54,76],"by":[34],"information":[36,59,66],"retrieval":[37,67],"research":[38],"community":[39],"knowledge":[41],"sharing":[42],"in":[43,45,57],"many":[46],"ways;":[47],"example,":[49],"experimentations":[56],"cross-lingual":[58,61],"retrieval,":[60],"link":[62],"discovery,":[63],"or":[64],"omni-lingual":[65],"research.":[68],"Furthermore,":[69],"translated":[71],"CJK":[72],"articles":[73],"to":[77],"further":[78],"expand":[79],"current":[81],"coverage":[82],"of":[83],"Wikipedia.":[86]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
