{"id":"https://openalex.org/W3094501123","doi":null,"title":"Investigating the True Performance of Transformers in Low-Resource Languages: A Case Study in Automatic Corpus Creation.","display_name":"Investigating the True Performance of Transformers in Low-Resource Languages: A Case Study in Automatic Corpus Creation.","publication_year":2020,"publication_date":"2020-10-22","ids":{"openalex":"https://openalex.org/W3094501123","mag":"3094501123"},"language":"en","primary_location":{"id":"mag:3094501123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.11574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048793278","display_name":"Jan Christian Blaise Cruz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Christian Blaise Cruz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017341185","display_name":"Jose Kristian Resabal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose Kristian Resabal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083112512","display_name":"James Wuh Lin","orcid":"https://orcid.org/0000-0003-0841-3646","observed_orcids":["https://orcid.org/0000-0003-0841-3646"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Lin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0841-3646","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048708863","display_name":"Dan John Velasco","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan John Velasco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017208830","display_name":"Charibeth Ko Cheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charibeth Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7519999742507935,"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/T10028","display_name":"Topic Modeling","score":0.7519999742507935,"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":0.23849999904632568,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0035000001080334187,"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/low-resource-languages","display_name":"low-resource languages","score":0.9330000281333923},{"id":"https://openalex.org/keywords/filipino-language","display_name":"Filipino language","score":0.8149999976158142},{"id":"https://openalex.org/keywords/natural-language-inference","display_name":"natural language inference","score":0.7979999780654907},{"id":"https://openalex.org/keywords/pre-trained-transformers","display_name":"pre-trained transformer models","score":0.7450000047683716},{"id":"https://openalex.org/keywords/electra","display_name":"Electra","score":0.9660000205039978},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9660000205039978},{"id":"https://openalex.org/keywords/news-articles","display_name":"news articles","score":0.5690000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042643666267395},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7607210874557495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6704778671264648},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6613810062408447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6546748280525208},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6301932334899902},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6009012460708618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823493003845215},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.49553215503692627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37354594469070435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06810835003852844},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3094501123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3094501123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W18159654","https://openalex.org/W1522301498","https://openalex.org/W2015014880","https://openalex.org/W2077724051","https://openalex.org/W2131744502","https://openalex.org/W2242645131","https://openalex.org/W2544860310","https://openalex.org/W2607892599","https://openalex.org/W2626778328","https://openalex.org/W2743945814","https://openalex.org/W2784121710","https://openalex.org/W2945886944","https://openalex.org/W2953084091","https://openalex.org/W2953109491","https://openalex.org/W2954835819","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970247882","https://openalex.org/W2980596743","https://openalex.org/W2982784916","https://openalex.org/W3006436762","https://openalex.org/W3013571468","https://openalex.org/W3022569409","https://openalex.org/W3031068414","https://openalex.org/W3034715004","https://openalex.org/W3092950978","https://openalex.org/W3127856874"],"related_works":["https://openalex.org/W3161697466","https://openalex.org/W3208594153","https://openalex.org/W3022569409","https://openalex.org/W3092950978","https://openalex.org/W7105212969","https://openalex.org/W2954835819","https://openalex.org/W7212685396","https://openalex.org/W6922532438","https://openalex.org/W7167833094","https://openalex.org/W4229067736"],"abstract_inverted_index":{"Transformers":[0],"represent":[1],"the":[2,42,51,93,100,112,118,155],"state-of-the-art":[3],"in":[4,9,15,18,99,121,151],"Natural":[5,73],"Language":[6,74],"Processing":[7],"(NLP)":[8],"recent":[10],"years,":[11],"proving":[12],"effective":[13],"even":[14],"tasks":[16],"done":[17],"low-resource":[19,80,101],"languages.":[20],"While":[21],"pretrained":[22,108],"transformers":[23,109],"for":[24,70,79],"these":[25],"languages":[26,81],"can":[27],"be":[28],"made,":[29],"it":[30],"is":[31],"challenging":[32],"to":[33,41,115,142],"measure":[34],"their":[35,146],"true":[36,147],"performance":[37,148],"and":[38,53,90],"capacity":[39],"due":[40],"lack":[43],"of":[44,55,157],"hard":[45],"benchmark":[46,77,97],"datasets,":[47],"as":[48,50],"well":[49],"difficulty":[52],"cost":[54],"producing":[56,72],"them.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,66,88,105,135],"present":[62],"three":[63],"contributions:":[64],"First,":[65],"propose":[67],"a":[68],"methodology":[69],"automatically":[71],"Inference":[75],"(NLI)":[76],"datasets":[78],"using":[82],"published":[83],"news":[84],"articles.":[85],"Through":[86],"this,":[87],"create":[89],"release":[91],"NewsPH-NLI,":[92],"first":[94],"sentence":[95],"entailment":[96],"dataset":[98,127],"Filipino":[102],"language.":[103],"Second,":[104],"produce":[106],"new":[107],"based":[110],"on":[111,125,138,145],"ELECTRA":[113],"technique":[114],"further":[116],"alleviate":[117],"resource":[119],"scarcity":[120],"Filipino,":[122],"benchmarking":[123],"them":[124],"our":[126],"against":[128],"other":[129],"commonly-used":[130],"transfer":[131,139],"learning":[132,140],"techniques.":[133],"Lastly,":[134],"perform":[136],"analyses":[137],"techniques":[141],"shed":[143],"light":[144],"when":[149],"operating":[150],"low-data":[152],"domains":[153],"through":[154],"use":[156],"degradation":[158],"tests.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2020-10-29T00:00:00"}