FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197744542> ?p ?o ?g. }

• W3197744542 abstract "Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient annotated data. Traditional fine-tuning of pre-trained models using only a few target samples can cause over-fitting. This can be quite limiting as most languages in the world are under-resourced. In this work, we investigate cross-lingual adaptation using a simple nearest-neighbor few-shot (<15 samples) inference technique for classification tasks. We experiment using a total of 16 distinct languages across two NLP tasks- XNLI and PAWS-X. Our approach consistently improves traditional fine-tuning using only a handful of labeled samples in target locales. We also demonstrate its generalization capability across tasks." @default.
• W3197744542 created "2021-09-13" @default.
• W3197744542 creator A5020054157 @default.
• W3197744542 creator A5046196738 @default.
• W3197744542 creator A5070002963 @default.
• W3197744542 date "2021-01-01" @default.
• W3197744542 modified "2023-10-16" @default.
• W3197744542 title "Nearest Neighbour Few-Shot Learning for Cross-lingual Classification" @default.
• W3197744542 cites W2601450892 @default.
• W3197744542 cites W2753160622 @default.
• W3197744542 cites W2775795276 @default.
• W3197744542 cites W2891555348 @default.
• W3197744542 cites W2932893307 @default.
• W3197744542 cites W2951775809 @default.
• W3197744542 cites W2963216553 @default.
• W3197744542 cites W2963341924 @default.
• W3197744542 cites W2963846996 @default.
• W3197744542 cites W2963907629 @default.
• W3197744542 cites W2970854433 @default.
• W3197744542 cites W2971105085 @default.
• W3197744542 cites W2995015695 @default.
• W3197744542 cites W3009586901 @default.
• W3197744542 cites W3011115117 @default.
• W3197744542 cites W3017342174 @default.
• W3197744542 cites W3021766370 @default.
• W3197744542 cites W3023125906 @default.
• W3197744542 cites W3023911605 @default.
• W3197744542 cites W3035390927 @default.
• W3197744542 cites W3042711927 @default.
• W3197744542 cites W3085479580 @default.
• W3197744542 cites W3091905774 @default.
• W3197744542 cites W3093517588 @default.
• W3197744542 cites W3097879195 @default.
• W3197744542 cites W3108878460 @default.
• W3197744542 doi "https://doi.org/10.18653/v1/2021.emnlp-main.131" @default.
• W3197744542 hasPublicationYear "2021" @default.
• W3197744542 type Work @default.
• W3197744542 sameAs 3197744542 @default.
• W3197744542 citedByCount "0" @default.
• W3197744542 crossrefType "proceedings-article" @default.
• W3197744542 hasAuthorship W3197744542A5020054157 @default.
• W3197744542 hasAuthorship W3197744542A5046196738 @default.
• W3197744542 hasAuthorship W3197744542A5070002963 @default.
• W3197744542 hasBestOaLocation W31977445421 @default.
• W3197744542 hasConcept C113238511 @default.
• W3197744542 hasConcept C119857082 @default.
• W3197744542 hasConcept C120665830 @default.
• W3197744542 hasConcept C121332964 @default.
• W3197744542 hasConcept C127413603 @default.
• W3197744542 hasConcept C134306372 @default.
• W3197744542 hasConcept C139807058 @default.
• W3197744542 hasConcept C153180895 @default.
• W3197744542 hasConcept C154945302 @default.
• W3197744542 hasConcept C159985019 @default.
• W3197744542 hasConcept C177148314 @default.
• W3197744542 hasConcept C178790620 @default.
• W3197744542 hasConcept C185592680 @default.
• W3197744542 hasConcept C188198153 @default.
• W3197744542 hasConcept C192562407 @default.
• W3197744542 hasConcept C204321447 @default.
• W3197744542 hasConcept C204323151 @default.
• W3197744542 hasConcept C2776214188 @default.
• W3197744542 hasConcept C2776434776 @default.
• W3197744542 hasConcept C2778344882 @default.
• W3197744542 hasConcept C33923547 @default.
• W3197744542 hasConcept C41008148 @default.
• W3197744542 hasConcept C51632099 @default.
• W3197744542 hasConcept C78519656 @default.
• W3197744542 hasConcept C95623464 @default.
• W3197744542 hasConceptScore W3197744542C113238511 @default.
• W3197744542 hasConceptScore W3197744542C119857082 @default.
• W3197744542 hasConceptScore W3197744542C120665830 @default.
• W3197744542 hasConceptScore W3197744542C121332964 @default.
• W3197744542 hasConceptScore W3197744542C127413603 @default.
• W3197744542 hasConceptScore W3197744542C134306372 @default.
• W3197744542 hasConceptScore W3197744542C139807058 @default.
• W3197744542 hasConceptScore W3197744542C153180895 @default.
• W3197744542 hasConceptScore W3197744542C154945302 @default.
• W3197744542 hasConceptScore W3197744542C159985019 @default.
• W3197744542 hasConceptScore W3197744542C177148314 @default.
• W3197744542 hasConceptScore W3197744542C178790620 @default.
• W3197744542 hasConceptScore W3197744542C185592680 @default.
• W3197744542 hasConceptScore W3197744542C188198153 @default.
• W3197744542 hasConceptScore W3197744542C192562407 @default.
• W3197744542 hasConceptScore W3197744542C204321447 @default.
• W3197744542 hasConceptScore W3197744542C204323151 @default.
• W3197744542 hasConceptScore W3197744542C2776214188 @default.
• W3197744542 hasConceptScore W3197744542C2776434776 @default.
• W3197744542 hasConceptScore W3197744542C2778344882 @default.
• W3197744542 hasConceptScore W3197744542C33923547 @default.
• W3197744542 hasConceptScore W3197744542C41008148 @default.
• W3197744542 hasConceptScore W3197744542C51632099 @default.
• W3197744542 hasConceptScore W3197744542C78519656 @default.
• W3197744542 hasConceptScore W3197744542C95623464 @default.
• W3197744542 hasLocation W31977445421 @default.
• W3197744542 hasLocation W31977445422 @default.
• W3197744542 hasOpenAccess W3197744542 @default.
• W3197744542 hasPrimaryLocation W31977445421 @default.
• W3197744542 hasRelatedWork W2130997612 @default.
• W3197744542 hasRelatedWork W2146076056 @default.

• next