{"id":"https://openalex.org/W4366308792","doi":"https://doi.org/10.1109/ictai56018.2022.00045","title":"Expand-Extract: A Parallel Corpus Mining Framework from Comparable Corpora for English-Myanmar Machine Translation","display_name":"Expand-Extract: A Parallel Corpus Mining Framework from Comparable Corpora for English-Myanmar Machine Translation","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4366308792","doi":"https://doi.org/10.1109/ictai56018.2022.00045"},"language":"en","primary_location":{"id":"doi:10.1109/ictai56018.2022.00045","doi":"https://doi.org/10.1109/ictai56018.2022.00045","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00045","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5055349923","display_name":"May Myo Zin","orcid":"https://orcid.org/0000-0003-1315-7704","observed_orcids":["https://orcid.org/0000-0003-1315-7704"]},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"May Myo Zin","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055898374","display_name":"Teeradaj Racharak","orcid":"https://orcid.org/0000-0002-8823-2361","observed_orcids":["https://orcid.org/0000-0002-8823-2361"]},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Teeradaj Racharak","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077641909","display_name":"Le-Minh Nguyen","orcid":"https://orcid.org/0000-0002-2265-1010","observed_orcids":["https://orcid.org/0000-0002-2265-1010"]},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minh le Nguyen","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Scinece and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17280539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"259","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9965999722480774,"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":0.0017999999690800905,"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/T10759","display_name":"Translation Studies and Practices","score":0.00039999998989515007,"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/comparable-corpora","display_name":"comparable corpora","score":0.9390000104904175},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9649999737739563},{"id":"https://openalex.org/keywords/back-translation","display_name":"back-translation","score":0.7080000042915344},{"id":"https://openalex.org/keywords/self-training","display_name":"self-training","score":0.8709999918937683},{"id":"https://openalex.org/keywords/synthetic-data-augmentation","display_name":"synthetic data augmentation","score":0.6370000243186951}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8991705179214478},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8608511090278625},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.8282067775726318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6996257305145264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6814080476760864},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6536498069763184},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6049259901046753},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.46032774448394775},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai56018.2022.00045","doi":"https://doi.org/10.1109/ictai56018.2022.00045","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai56018.2022.00045","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W117861810","https://openalex.org/W2101105183","https://openalex.org/W2105673178","https://openalex.org/W2124807415","https://openalex.org/W2164479068","https://openalex.org/W2211796614","https://openalex.org/W2304348025","https://openalex.org/W2435130738","https://openalex.org/W2533848870","https://openalex.org/W2561274697","https://openalex.org/W2573761686","https://openalex.org/W2626778328","https://openalex.org/W2798389157","https://openalex.org/W2805411799","https://openalex.org/W2805430026","https://openalex.org/W2807849360","https://openalex.org/W2899337869","https://openalex.org/W2905749056","https://openalex.org/W2949405462","https://openalex.org/W2963216553","https://openalex.org/W2963373809","https://openalex.org/W2976223659","https://openalex.org/W2988739750","https://openalex.org/W2995917377","https://openalex.org/W3039695075","https://openalex.org/W3128140386","https://openalex.org/W3156404059","https://openalex.org/W3215556358","https://openalex.org/W4205866829","https://openalex.org/W4285199256","https://openalex.org/W6769871666"],"related_works":["https://openalex.org/W2904817833","https://openalex.org/W4385225022","https://openalex.org/W4400324892","https://openalex.org/W3155542537","https://openalex.org/W3215556358","https://openalex.org/W4386307686","https://openalex.org/W1835075965","https://openalex.org/W2786253471","https://openalex.org/W2986030184","https://openalex.org/W2918449741"],"abstract_inverted_index":{"High-quality":[0],"neural":[1],"machine":[2],"translation":[3,172],"(NMT)":[4],"systems":[5,135,176],"rely":[6],"on":[7,137,178],"the":[8,23,50,65,80,91,102,119,126,133,138,154,167,179],"availability":[9],"of":[10,26,82,128,140,159,174],"large-scale":[11],"and":[12,60,90,147,165],"reliable":[13,162],"parallel":[14,24,47,99,108,115,141,163,181],"data.":[15],"Since":[16],"Myanmar":[17],"language":[18,28],"is":[19,30,157],"a":[20,39,46,161],"low-resource":[21,120],"language,":[22],"corpus":[25,48,116,169],"English-Myanmar":[27,121],"pair":[29],"sparse":[31],"in":[32],"volume.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38],"simple":[40],"yet":[41],"effective":[42],"framework":[43,146,156],"to":[44,78,97,113],"create":[45],"from":[49,101],"available":[51],"comparable":[52,84,104],"corpora.":[53,85,105],"Our":[54],"proposed":[55,92,155],"system":[56,70],"first":[57],"uses":[58],"self-training":[59],"back-translation":[61],"approaches":[62],"together":[63],"with":[64],"denoising-based":[66],"automatic":[67,186],"post-editing":[68],"(DbAPE)":[69],"for":[71],"augmenting":[72],"synthetic":[73],"datasets":[74],"that":[75,153,166],"are":[76,95],"used":[77,112],"expand":[79],"size":[81],"existing":[83,149,180],"Then,":[86],"LaBSE-based":[87],"sentence":[88],"embeddings":[89],"scoring":[93],"function":[94],"applied":[96],"extract":[98],"sentences":[100,109],"expanded":[103],"The":[106],"extracted":[107],"can":[110],"be":[111],"supplement":[114],"when":[117],"training":[118],"NMT":[122,134],"systems.":[123],"We":[124,151],"investigate":[125],"effectiveness":[127],"our":[129,145],"methods":[130],"by":[131,144,185],"evaluating":[132],"trained":[136,177],"concatenation":[139],"data":[142],"created":[143,168],"an":[148],"dataset.":[150],"show":[152],"capable":[158],"creating":[160],"corpus,":[164],"substantially":[170],"increases":[171],"quality":[173],"MT":[175],"data,":[182],"as":[183],"measured":[184],"evaluation":[187],"metrics.":[188]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-04-20T00:00:00"}