Language graph distillation, which uses forward and backward multi-hop translation paths to generate pseudo-parallel data, raises average BLEU by 3.13 points on selected low-resource pairs in a 9-language TED talks pilot.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Language Graph Distillation for Low-Resource Machine Translation
Language graph distillation, which uses forward and backward multi-hop translation paths to generate pseudo-parallel data, raises average BLEU by 3.13 points on selected low-resource pairs in a 9-language TED talks pilot.