Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
CoRR(2023)
摘要
Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy
for neural machine translation (NMT) models. The underlying assumption is that
model probability correlates well with human judgment, with better translations
getting assigned a higher score by the model. However, research has shown that
this assumption does not always hold, and generation quality can be improved by
decoding to optimize a utility function backed by a metric or
quality-estimation signal, as is done by Minimum Bayes Risk (MBR) or
Quality-Aware decoding. The main disadvantage of these approaches is that they
require an additional model to calculate the utility function during decoding,
significantly increasing the computational cost. In this paper, we propose to
make the NMT models themselves quality-aware by training them to estimate the
quality of their own output. Using this approach for MBR decoding we can
drastically reduce the size of the candidate list, resulting in a speed-up of
two-orders of magnitude. When applying our method to MAP decoding we obtain
quality gains similar or even superior to quality reranking approaches, but
with the efficiency of single pass decoding.
更多查看译文
关键词
translation,models,quality-aware
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要