The paper claims LLM prompting can translate a no-resource language at BLEU 0.45-0.6, but the appendix suggests the input may have been English glosses, not Paiute, so the central claim is not established.
Data augmentation for low-resource neural machine translation.Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 1:567–573, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches
The paper claims LLM prompting can translate a no-resource language at BLEU 0.45-0.6, but the appendix suggests the input may have been English glosses, not Paiute, so the central claim is not established.