Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385570855> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4385570855 abstract "Few-shot cross-lingual transfer, fine-tuning Multilingual Masked Language Model (MMLM) with source language labeled data and a small amount of target language labeled data, provides excellent performance in the target language.However, if no labeled data in the target language are available, they need to be created through human annotations.In this study, we devise a metric to select annotation candidates from an unlabeled data pool that efficiently enhance accuracy for few-shot cross-lingual transfer.It is known that training a model with hard examples is important to improve the model’s performance.Therefore, we first identify examples that MMLM cannot solve in a zero-shot cross-lingual transfer setting and demonstrate that it is hard to predict peculiar examples in the target language, i.e., the examples distant from the source language examples in cross-lingual semantic space of the MMLM.We then choose high peculiarity examples as annotation candidates and perform few-shot cross-lingual transfer.In comprehensive experiments with 20 languages and 6 tasks, we demonstrate that the high peculiarity examples improve the target language accuracy compared to other candidate selection methods proposed in previous studies." @default.
- W4385570855 created "2023-08-05" @default.
- W4385570855 creator A5061931124 @default.
- W4385570855 creator A5066853717 @default.
- W4385570855 date "2023-01-01" @default.
- W4385570855 modified "2023-09-24" @default.
- W4385570855 title "Enhancing Few-shot Cross-lingual Transfer with Target Language Peculiar Examples" @default.
- W4385570855 doi "https://doi.org/10.18653/v1/2023.findings-acl.47" @default.
- W4385570855 hasPublicationYear "2023" @default.
- W4385570855 type Work @default.
- W4385570855 citedByCount "0" @default.
- W4385570855 crossrefType "proceedings-article" @default.
- W4385570855 hasAuthorship W4385570855A5061931124 @default.
- W4385570855 hasAuthorship W4385570855A5066853717 @default.
- W4385570855 hasBestOaLocation W43855708551 @default.
- W4385570855 hasConcept C137293760 @default.
- W4385570855 hasConcept C150899416 @default.
- W4385570855 hasConcept C154945302 @default.
- W4385570855 hasConcept C162324750 @default.
- W4385570855 hasConcept C173608175 @default.
- W4385570855 hasConcept C176217482 @default.
- W4385570855 hasConcept C178790620 @default.
- W4385570855 hasConcept C185592680 @default.
- W4385570855 hasConcept C204321447 @default.
- W4385570855 hasConcept C21547014 @default.
- W4385570855 hasConcept C2776145971 @default.
- W4385570855 hasConcept C2776175482 @default.
- W4385570855 hasConcept C2776321320 @default.
- W4385570855 hasConcept C2778344882 @default.
- W4385570855 hasConcept C41008148 @default.
- W4385570855 hasConcept C81917197 @default.
- W4385570855 hasConceptScore W4385570855C137293760 @default.
- W4385570855 hasConceptScore W4385570855C150899416 @default.
- W4385570855 hasConceptScore W4385570855C154945302 @default.
- W4385570855 hasConceptScore W4385570855C162324750 @default.
- W4385570855 hasConceptScore W4385570855C173608175 @default.
- W4385570855 hasConceptScore W4385570855C176217482 @default.
- W4385570855 hasConceptScore W4385570855C178790620 @default.
- W4385570855 hasConceptScore W4385570855C185592680 @default.
- W4385570855 hasConceptScore W4385570855C204321447 @default.
- W4385570855 hasConceptScore W4385570855C21547014 @default.
- W4385570855 hasConceptScore W4385570855C2776145971 @default.
- W4385570855 hasConceptScore W4385570855C2776175482 @default.
- W4385570855 hasConceptScore W4385570855C2776321320 @default.
- W4385570855 hasConceptScore W4385570855C2778344882 @default.
- W4385570855 hasConceptScore W4385570855C41008148 @default.
- W4385570855 hasConceptScore W4385570855C81917197 @default.
- W4385570855 hasLocation W43855708551 @default.
- W4385570855 hasOpenAccess W4385570855 @default.
- W4385570855 hasPrimaryLocation W43855708551 @default.
- W4385570855 hasRelatedWork W2134159029 @default.
- W4385570855 hasRelatedWork W2164990725 @default.
- W4385570855 hasRelatedWork W2359001871 @default.
- W4385570855 hasRelatedWork W2889705046 @default.
- W4385570855 hasRelatedWork W3038321203 @default.
- W4385570855 hasRelatedWork W3164871893 @default.
- W4385570855 hasRelatedWork W3193920202 @default.
- W4385570855 hasRelatedWork W3198431588 @default.
- W4385570855 hasRelatedWork W4287660331 @default.
- W4385570855 hasRelatedWork W4309865838 @default.
- W4385570855 isParatext "false" @default.
- W4385570855 isRetracted "false" @default.
- W4385570855 workType "article" @default.