{"id":"https://openalex.org/W3163094616","doi":"https://doi.org/10.1142/s2717554520500174","title":"Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation","display_name":"Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3163094616","doi":"https://doi.org/10.1142/s2717554520500174","mag":"3163094616"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554520500174","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554520500174","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-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/A5035929568","display_name":"Rashmini Naranpanawa","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":true,"raw_author_name":"Rashmini Naranpanawa","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056352888","display_name":"Ravinga Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Ravinga Perera","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022032330","display_name":"Thilakshi Fonseka","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Thilakshi Fonseka","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049911731","display_name":"Uthayasanker Thayasivam","orcid":"https://orcid.org/0000-0002-3936-8174"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Uthayasanker Thayasivam","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa, Katubedda 10400, Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035929568"],"corresponding_institution_ids":["https://openalex.org/I195740183"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6599399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"30","issue":"04","first_page":"2050017","last_page":"2050017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9951000213623047,"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/machine-translation","display_name":"Machine translation","score":0.8430933952331543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8379403352737427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7430341839790344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6645702719688416},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6310189366340637},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6169928312301636},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4629237651824951},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.45321789383888245},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.42776575684547424},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42419394850730896},{"id":"https://openalex.org/keywords/english-vocabulary","display_name":"English vocabulary","score":0.42257213592529297},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4196477234363556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38001248240470886},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3305889964103699},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2319076657295227},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05668693780899048}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8430933952331543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379403352737427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7430341839790344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645702719688416},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6310189366340637},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6169928312301636},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4629237651824951},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.45321789383888245},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.42776575684547424},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42419394850730896},{"id":"https://openalex.org/C3017914614","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English vocabulary","level":3,"score":0.42257213592529297},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4196477234363556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38001248240470886},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3305889964103699},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2319076657295227},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05668693780899048},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2717554520500174","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554520500174","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2124807415","https://openalex.org/W2886292623","https://openalex.org/W2903114443","https://openalex.org/W2912061877","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2963979492","https://openalex.org/W2971120622","https://openalex.org/W3035207248"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2990400634","https://openalex.org/W2313858059","https://openalex.org/W2089389390","https://openalex.org/W1565387327","https://openalex.org/W2921692863","https://openalex.org/W2787109023","https://openalex.org/W1621562970","https://openalex.org/W1980957807","https://openalex.org/W3163094616"],"abstract_inverted_index":{"Neural":[0],"machine":[1,15],"translation":[2,16,89],"(NMT)":[3],"is":[4,21,30],"a":[5,36,109,137,143],"remarkable":[6],"approach":[7,107],"which":[8,105],"performs":[9],"much":[10],"better":[11],"than":[12],"the":[13,52,92,126],"Statistical":[14],"(SMT)":[17],"models":[18,118],"when":[19,132],"there":[20],"an":[22],"abundance":[23],"of":[24,54,101,142],"parallel":[25,145],"corpus.":[26,146],"However,":[27],"vanilla":[28],"NMT":[29,128],"primarily":[31],"based":[32],"upon":[33],"word-level":[34],"with":[35,125],"fixed":[37],"vocabulary.":[38],"Therefore,":[39],"low":[40,71],"resource":[41,72],"morphologically":[42],"rich":[43,138],"languages":[44],"such":[45],"as":[46],"Sinhala":[47,114],"are":[48],"mostly":[49],"affected":[50],"by":[51,74],"out":[53],"vocabulary":[55,77],"(OOV)":[56],"and":[57,94],"Rare":[58],"word":[59],"problems.":[60],"Recent":[61],"advancements":[62],"in":[63],"subword":[64,97,106,121],"techniques":[65,98],"have":[66],"opened":[67],"up":[68],"opportunities":[69],"for":[70],"communities":[73],"enabling":[75],"open":[76],"translation.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"extend":[83],"our":[84],"recently":[85],"published":[86],"state-of-the-art":[87,127],"EN-SI":[88],"system":[90],"using":[91],"transformer":[93],"explore":[95],"standard":[96],"on":[99,112],"top":[100],"it":[102],"to":[103],"identify":[104],"has":[108],"greater":[110],"effect":[111],"English":[113,134],"language":[115,140],"pair.":[116],"Our":[117],"demonstrate":[119],"that":[120],"segmentation":[122],"strategies":[123],"along":[124],"can":[129],"perform":[130],"remarkably":[131],"translating":[133],"sentences":[135],"into":[136],"morphology":[139],"regardless":[141],"large":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
