{"id":"https://openalex.org/W4237844987","doi":"https://doi.org/10.1002/asi.20737","title":"Active learning for constructing transliteration lexicons from the Web","display_name":"Active learning for constructing transliteration lexicons from the Web","publication_year":2007,"publication_date":"2007-10-18","ids":{"openalex":"https://openalex.org/W4237844987","doi":"https://doi.org/10.1002/asi.20737"},"language":"en","primary_location":{"id":"doi:10.1002/asi.20737","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20737","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20737","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20737","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027993773","display_name":"Jin\u2010Shea Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jin\u2010Shea Kuo","raw_affiliation_strings":["Dept. of Electrical Engineering, National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100831531","display_name":"Ying\u2010Kuei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying\u2010Kuei Yang","raw_affiliation_strings":["Dept. of Electrical Engineering, National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027993773"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.42501007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"59","issue":"1","first_page":"126","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.828403115272522},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.8027564287185669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7246206998825073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5851872563362122},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5755029916763306},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.47982048988342285},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45665442943573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4447583556175232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828403115272522},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8027564287185669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7246206998825073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5851872563362122},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5755029916763306},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.47982048988342285},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45665442943573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4447583556175232},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/asi.20737","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20737","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20737","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/asi.20737","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20737","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20737","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334744","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4237844987.pdf","grobid_xml":"https://content.openalex.org/works/W4237844987.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W125241024","https://openalex.org/W182831726","https://openalex.org/W1513874326","https://openalex.org/W1553262910","https://openalex.org/W1618885279","https://openalex.org/W1831974383","https://openalex.org/W1950854090","https://openalex.org/W1987777228","https://openalex.org/W2019614587","https://openalex.org/W2024181699","https://openalex.org/W2032571942","https://openalex.org/W2041232209","https://openalex.org/W2049633694","https://openalex.org/W2053705431","https://openalex.org/W2055543848","https://openalex.org/W2066636486","https://openalex.org/W2095629250","https://openalex.org/W2102749417","https://openalex.org/W2115513413","https://openalex.org/W2119665060","https://openalex.org/W2122789960","https://openalex.org/W2127361019","https://openalex.org/W2130716237","https://openalex.org/W2134534213","https://openalex.org/W2153819437","https://openalex.org/W2913739034","https://openalex.org/W2949071206","https://openalex.org/W4229679882","https://openalex.org/W6636472884","https://openalex.org/W6647342240","https://openalex.org/W6677945094","https://openalex.org/W6703490699"],"related_works":["https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W3153459181","https://openalex.org/W2371976984","https://openalex.org/W2352160949","https://openalex.org/W2378436233","https://openalex.org/W2069398544","https://openalex.org/W4293870971","https://openalex.org/W1831473261","https://openalex.org/W4206195464"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"article":[2],"presents":[3],"an":[4],"adaptive":[5],"learning":[6,22,43,47,59,80],"framework":[7,93],"for":[8],"Phonetic":[9],"Similarity":[10],"Modeling":[11],"(PSM)":[12],"that":[13,49,90],"supports":[14],"the":[15,37,41,45,62,70,75,91],"automatic":[16],"construction":[17],"of":[18,55,85],"transliteration":[19,31,67],"lexicons.":[20],"The":[21,58],"algorithm":[23,81],"starts":[24],"with":[25],"minimum":[26],"prior":[27],"knowledge":[28,34],"about":[29],"machine":[30],"and":[32,44,64,78],"acquires":[33],"iteratively":[35],"from":[36],"Web.":[38],"We":[39,73],"study":[40],"unsupervised":[42],"active":[46],"strategies":[48],"minimize":[50],"human":[51],"supervision":[52],"in":[53],"terms":[54],"data":[56],"labeling.":[57],"process":[60],"refines":[61],"PSM":[63,77],"constructs":[65],"a":[66,83],"lexicon":[68],"at":[69],"same":[71],"time.":[72],"evaluate":[74],"proposed":[76,92],"its":[79],"through":[82],"series":[84],"systematic":[86],"experiments,":[87],"which":[88],"show":[89],"is":[94],"reliably":[95],"effective":[96],"on":[97],"two":[98],"independent":[99],"databases.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
