{"id":"https://openalex.org/W4310581413","doi":"https://doi.org/10.1109/ialp57159.2022.9961269","title":"How Much Data is Sufficient for Neural Transliteration?","display_name":"How Much Data is Sufficient for Neural Transliteration?","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4310581413","doi":"https://doi.org/10.1109/ialp57159.2022.9961269"},"language":"en","primary_location":{"id":"doi:10.1109/ialp57159.2022.9961269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp57159.2022.9961269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-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/A5101530732","display_name":"Zhijuan Wang","orcid":"https://orcid.org/0000-0003-4027-3591"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhijuan Wang","raw_affiliation_strings":["School of Information Engineering, Minzu University of China","National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448036","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Li","raw_affiliation_strings":["School of Information Engineering, Minzu University of China","National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773044","display_name":"Xiaobing Zhao","orcid":"https://orcid.org/0000-0003-1217-8650"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Zhao","raw_affiliation_strings":["School of Information Engineering, Minzu University of China","National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Minzu University of China","institution_ids":["https://openalex.org/I145897649"]},{"raw_affiliation_string":"National Language Resource Monitoring and Research Center of Minority Languages, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101530732"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":0.2652,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62218789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"470","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/transliteration","display_name":"Transliteration","score":0.9847831726074219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7969211935997009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6495913863182068},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6457920670509338},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6107978820800781},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5811322331428528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5010700225830078},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3345756530761719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07039159536361694}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.9847831726074219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969211935997009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6495913863182068},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6457920670509338},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6107978820800781},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5811322331428528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5010700225830078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345756530761719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07039159536361694},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp57159.2022.9961269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp57159.2022.9961269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W157259314","https://openalex.org/W2090755665","https://openalex.org/W2130942839","https://openalex.org/W2166979461","https://openalex.org/W2545605631","https://openalex.org/W2757988102","https://openalex.org/W2805430026","https://openalex.org/W2837112844","https://openalex.org/W2885158679","https://openalex.org/W2885242435","https://openalex.org/W2885678784","https://openalex.org/W2886440583","https://openalex.org/W2887185954","https://openalex.org/W2887660679","https://openalex.org/W2890511566","https://openalex.org/W2963042536","https://openalex.org/W2964343439","https://openalex.org/W3166486483","https://openalex.org/W4288286832","https://openalex.org/W4385245566","https://openalex.org/W6606341813","https://openalex.org/W6679436768","https://openalex.org/W6684666790","https://openalex.org/W6729116077","https://openalex.org/W6739901393","https://openalex.org/W6752264108","https://openalex.org/W6752933292","https://openalex.org/W6764828761","https://openalex.org/W6795479802","https://openalex.org/W6898505805"],"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/W2354361711","https://openalex.org/W4362573963","https://openalex.org/W2069398544","https://openalex.org/W4310581413"],"abstract_inverted_index":{"Data":[0],"size":[1,94,125],"is":[2,13,23,42,95,102,126,133,150],"vital":[3],"for":[4,16,25,44,81,153],"neural":[5,28,38,78,156],"transliteration.":[6,49],"But":[7],"getting":[8],"lots":[9],"of":[10,99,106,130,137],"transliteration":[11,29,40,79,158],"pairs":[12],"difficult,":[14],"especially":[15],"low-resource":[17],"languages.":[18],"So":[19],"how":[20],"much":[21],"data":[22,65,84,93,124,149],"sufficient":[24,152],"an":[26],"often-used":[27],"model":[30,41],"with":[31,61],"good":[32,46],"performance?":[33],"Firstly,":[34],"the":[35,70,82,91,97,107,116,122,128,138,154],"Tensor2Tensor":[36,155],"(T2T)":[37],"Transformer":[39,157],"selected":[43],"its":[45],"performance":[47],"in":[48,74],"Then":[50],"select":[51],"all":[52,112,143],"language":[53],"pair":[54],"datasets":[55,73],"from":[56,69],"English":[57],"to":[58,87],"other":[59],"languages":[60],"more":[62,103,134],"than":[63,104,135],"40k":[64],"and":[66,115],"freely":[67],"available":[68],"website":[71],"(six":[72],"total).":[75],"Afterwards,":[76],"conduct":[77],"experiments":[80],"six":[83,100,131],"sets.":[85],"According":[86],"experimental":[88],"results,":[89],"when":[90],"training":[92,113,123,144,148],"20k,":[96],"accuracy":[98,109,117,129,140],"tasks":[101,132],"90%":[105],"best":[108,139],"based":[110,141],"on":[111,142],"data,":[114],"can":[118],"exceed":[119],"0.45.":[120],"When":[121],"15k,":[127],"85%":[136],"data.":[145],"Therefore,":[146],"20k":[147],"likely":[151],"model.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}