conftrace_

sequence-level loss

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

exposure bia (2) machine translation (2) token-level loss (1) reward augmented maximum likelihood (1) automatic post-editing (1) neural network (1) multi-source model (1) translation edit rate (1) multi-source transformer (1) bilingual evaluation understudy (1)

Papers

Multi-source transformer with combined losses for automatic post editing EMNLP 2018 Token-level and sequence-level loss smoothing for RNN language models ACL 2018