Generating several candidate translations per source sentence for knowledge distillation yields better small multilingual translators than standard single-hypothesis distillation, especially in low-resource settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages
Generating several candidate translations per source sentence for knowledge distillation yields better small multilingual translators than standard single-hypothesis distillation, especially in low-resource settings.