Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking
This work proposes Quit (Quantifying Uncertainty for Incremental Termination), a novel early-stopping strategy for the entire generation--reranking pipeline that incrementally generates and reranks candidates, stopping when the best reranking score stabilizes.
Guang Chen, Boxuan Lyu, Hidetaka Kamigaito et al.
· 0 citations