MBR decoding is reformulated via a noisy-channel decomposition into four weighted probabilistic terms, revealing that channel importance is metric-specific and task-agnostic, and that reweighting can improve performance.
Title resolution pending
1 Pith paper cite this work, alongside 253 external citations. Polarity classification is still indexing.
1
Pith paper citing it
253
external citations · external index
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Noisy-Channel Minimum Bayes Risk Decoding
MBR decoding is reformulated via a noisy-channel decomposition into four weighted probabilistic terms, revealing that channel importance is metric-specific and task-agnostic, and that reweighting can improve performance.