Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173829323> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3173829323 abstract "Multilingual Transformer-based language models, usually pretrained on more than 100 languages, have been shown to achieve outstanding results in a wide range of cross-lingual transfer tasks. However, it remains unknown whether the optimization for different languages conditions the capacity of the models to generalize over syntactic structures, and how languages with syntactic phenomena of different complexity are affected. In this work, we explore the syntactic generalization capabilities of the monolingual and multilingual versions of BERT and RoBERTa. More specifically, we evaluate the syntactic generalization potential of the models on English and Spanish tests, comparing the syntactic abilities of monolingual and multilingual models on the same language (English), and of multilingual models on two different languages (English and Spanish). For English, we use the available SyntaxGym test suite; for Spanish, we introduce SyntaxGymES, a novel ensemble of targeted syntactic tests in Spanish, designed to evaluate the syntactic generalization capabilities of language models through the SyntaxGym online platform." @default.
- W3173829323 created "2021-07-05" @default.
- W3173829323 creator A5043850175 @default.
- W3173829323 creator A5066801751 @default.
- W3173829323 creator A5077016111 @default.
- W3173829323 creator A5087323271 @default.
- W3173829323 date "2021-01-01" @default.
- W3173829323 modified "2023-09-27" @default.
- W3173829323 title "Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models" @default.
- W3173829323 cites W2531882892 @default.
- W3173829323 cites W2888922637 @default.
- W3173829323 cites W2891399254 @default.
- W3173829323 cites W2918996109 @default.
- W3173829323 cites W2921890305 @default.
- W3173829323 cites W2946359678 @default.
- W3173829323 cites W2962961857 @default.
- W3173829323 cites W2963341956 @default.
- W3173829323 cites W2963751529 @default.
- W3173829323 cites W2964204621 @default.
- W3173829323 cites W2964303116 @default.
- W3173829323 cites W2965373594 @default.
- W3173829323 cites W2970597249 @default.
- W3173829323 cites W2972896975 @default.
- W3173829323 cites W2978017171 @default.
- W3173829323 cites W2996728628 @default.
- W3173829323 cites W3015766957 @default.
- W3173829323 cites W3018732874 @default.
- W3173829323 cites W3031001133 @default.
- W3173829323 cites W3035064549 @default.
- W3173829323 cites W3035390927 @default.
- W3173829323 cites W3037115370 @default.
- W3173829323 cites W3088059392 @default.
- W3173829323 cites W3088382025 @default.
- W3173829323 cites W3168987555 @default.
- W3173829323 doi "https://doi.org/10.18653/v1/2021.findings-acl.333" @default.
- W3173829323 hasPublicationYear "2021" @default.
- W3173829323 type Work @default.
- W3173829323 sameAs 3173829323 @default.
- W3173829323 citedByCount "0" @default.
- W3173829323 crossrefType "proceedings-article" @default.
- W3173829323 hasAuthorship W3173829323A5043850175 @default.
- W3173829323 hasAuthorship W3173829323A5066801751 @default.
- W3173829323 hasAuthorship W3173829323A5077016111 @default.
- W3173829323 hasAuthorship W3173829323A5087323271 @default.
- W3173829323 hasBestOaLocation W31738293231 @default.
- W3173829323 hasConcept C119599485 @default.
- W3173829323 hasConcept C127413603 @default.
- W3173829323 hasConcept C137293760 @default.
- W3173829323 hasConcept C154945302 @default.
- W3173829323 hasConcept C165801399 @default.
- W3173829323 hasConcept C204321447 @default.
- W3173829323 hasConcept C41008148 @default.
- W3173829323 hasConcept C66322947 @default.
- W3173829323 hasConceptScore W3173829323C119599485 @default.
- W3173829323 hasConceptScore W3173829323C127413603 @default.
- W3173829323 hasConceptScore W3173829323C137293760 @default.
- W3173829323 hasConceptScore W3173829323C154945302 @default.
- W3173829323 hasConceptScore W3173829323C165801399 @default.
- W3173829323 hasConceptScore W3173829323C204321447 @default.
- W3173829323 hasConceptScore W3173829323C41008148 @default.
- W3173829323 hasConceptScore W3173829323C66322947 @default.
- W3173829323 hasLocation W31738293231 @default.
- W3173829323 hasLocation W31738293232 @default.
- W3173829323 hasLocation W31738293233 @default.
- W3173829323 hasOpenAccess W3173829323 @default.
- W3173829323 hasPrimaryLocation W31738293231 @default.
- W3173829323 hasRelatedWork W142374489 @default.
- W3173829323 hasRelatedWork W1563618553 @default.
- W3173829323 hasRelatedWork W1803932089 @default.
- W3173829323 hasRelatedWork W2148757832 @default.
- W3173829323 hasRelatedWork W2359001871 @default.
- W3173829323 hasRelatedWork W3033862527 @default.
- W3173829323 hasRelatedWork W3097571385 @default.
- W3173829323 hasRelatedWork W3107474891 @default.
- W3173829323 hasRelatedWork W3196747313 @default.
- W3173829323 hasRelatedWork W4287761227 @default.
- W3173829323 isParatext "false" @default.
- W3173829323 isRetracted "false" @default.
- W3173829323 magId "3173829323" @default.
- W3173829323 workType "article" @default.