Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129648567> ?p ?o ?g. }
- W3129648567 abstract "Pretrained language models are now of widespread use in Natural Language Processing. Despite their success, applying them to Low Resource languages is still a huge challenge. Although Multilingual models hold great promise, applying them to specific low-resource languages e.g. Roman Urdu can be excessive. In this paper, we show how the code-switching property of languages may be used to perform cross-lingual transfer learning from a corresponding high resource language. We also show how this transfer learning technique termed Bilingual Language Modeling can be used to produce better performing models for Roman Urdu. To enable training and experimentation, we also present a collection of novel corpora for Roman Urdu extracted from various sources and social networking sites, e.g. Twitter. We train Monolingual, Multilingual, and Bilingual models of Roman Urdu - the proposed bilingual model achieves 23% accuracy compared to the 2% and 11% of the monolingual and multilingual models respectively in the Masked Language Modeling (MLM) task." @default.
- W3129648567 created "2021-03-01" @default.
- W3129648567 creator A5026645452 @default.
- W3129648567 creator A5057413825 @default.
- W3129648567 creator A5061521072 @default.
- W3129648567 date "2021-02-22" @default.
- W3129648567 modified "2023-09-27" @default.
- W3129648567 title "Bilingual Language Modeling, A transfer learning technique for Roman Urdu." @default.
- W3129648567 cites W2013962395 @default.
- W3129648567 cites W2114359199 @default.
- W3129648567 cites W2115222200 @default.
- W3129648567 cites W2117130368 @default.
- W3129648567 cites W2118090838 @default.
- W3129648567 cites W2118788272 @default.
- W3129648567 cites W2132339004 @default.
- W3129648567 cites W2171190214 @default.
- W3129648567 cites W2182195832 @default.
- W3129648567 cites W2229725139 @default.
- W3129648567 cites W2250539671 @default.
- W3129648567 cites W2251765408 @default.
- W3129648567 cites W2339779833 @default.
- W3129648567 cites W2427527485 @default.
- W3129648567 cites W2626778328 @default.
- W3129648567 cites W2766020882 @default.
- W3129648567 cites W2786363455 @default.
- W3129648567 cites W2787560479 @default.
- W3129648567 cites W2798836595 @default.
- W3129648567 cites W2798908575 @default.
- W3129648567 cites W2799054028 @default.
- W3129648567 cites W2883300051 @default.
- W3129648567 cites W2886424491 @default.
- W3129648567 cites W2890842468 @default.
- W3129648567 cites W2901949782 @default.
- W3129648567 cites W2910987184 @default.
- W3129648567 cites W2946676565 @default.
- W3129648567 cites W2949402715 @default.
- W3129648567 cites W2949433733 @default.
- W3129648567 cites W2950133940 @default.
- W3129648567 cites W2950594802 @default.
- W3129648567 cites W2950813464 @default.
- W3129648567 cites W2954996676 @default.
- W3129648567 cites W2958953787 @default.
- W3129648567 cites W2965373594 @default.
- W3129648567 cites W2988923581 @default.
- W3129648567 cites W2990188683 @default.
- W3129648567 cites W2990704537 @default.
- W3129648567 cites W2996580882 @default.
- W3129648567 cites W3005736358 @default.
- W3129648567 cites W3008110149 @default.
- W3129648567 cites W3012385961 @default.
- W3129648567 cites W3013840636 @default.
- W3129648567 cites W3014635508 @default.
- W3129648567 cites W3032532958 @default.
- W3129648567 cites W3036840722 @default.
- W3129648567 cites W3126005225 @default.
- W3129648567 cites W342285082 @default.
- W3129648567 cites W2914696592 @default.
- W3129648567 hasPublicationYear "2021" @default.
- W3129648567 type Work @default.
- W3129648567 sameAs 3129648567 @default.
- W3129648567 citedByCount "0" @default.
- W3129648567 crossrefType "posted-content" @default.
- W3129648567 hasAuthorship W3129648567A5026645452 @default.
- W3129648567 hasAuthorship W3129648567A5057413825 @default.
- W3129648567 hasAuthorship W3129648567A5061521072 @default.
- W3129648567 hasConcept C127413603 @default.
- W3129648567 hasConcept C138885662 @default.
- W3129648567 hasConcept C150899416 @default.
- W3129648567 hasConcept C154945302 @default.
- W3129648567 hasConcept C201995342 @default.
- W3129648567 hasConcept C204321447 @default.
- W3129648567 hasConcept C2777350258 @default.
- W3129648567 hasConcept C2779235283 @default.
- W3129648567 hasConcept C2780035574 @default.
- W3129648567 hasConcept C2780451532 @default.
- W3129648567 hasConcept C41008148 @default.
- W3129648567 hasConcept C41895202 @default.
- W3129648567 hasConceptScore W3129648567C127413603 @default.
- W3129648567 hasConceptScore W3129648567C138885662 @default.
- W3129648567 hasConceptScore W3129648567C150899416 @default.
- W3129648567 hasConceptScore W3129648567C154945302 @default.
- W3129648567 hasConceptScore W3129648567C201995342 @default.
- W3129648567 hasConceptScore W3129648567C204321447 @default.
- W3129648567 hasConceptScore W3129648567C2777350258 @default.
- W3129648567 hasConceptScore W3129648567C2779235283 @default.
- W3129648567 hasConceptScore W3129648567C2780035574 @default.
- W3129648567 hasConceptScore W3129648567C2780451532 @default.
- W3129648567 hasConceptScore W3129648567C41008148 @default.
- W3129648567 hasConceptScore W3129648567C41895202 @default.
- W3129648567 hasLocation W31296485671 @default.
- W3129648567 hasOpenAccess W3129648567 @default.
- W3129648567 hasPrimaryLocation W31296485671 @default.
- W3129648567 hasRelatedWork W1807656721 @default.
- W3129648567 hasRelatedWork W2132609289 @default.
- W3129648567 hasRelatedWork W2409439155 @default.
- W3129648567 hasRelatedWork W2890907172 @default.
- W3129648567 hasRelatedWork W2976042047 @default.
- W3129648567 hasRelatedWork W2983577274 @default.
- W3129648567 hasRelatedWork W2991300985 @default.
- W3129648567 hasRelatedWork W3012990076 @default.