arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.09600cs.CL
收藏

机器翻译质量评估中的预测不确定性研究

Exploring Prediction Uncertainty in Machine Translation Quality Estimation

University of Sheffield(谢菲尔德大学);University of Melbourne(墨尔本大学)

Daniel Beck, Lucia Specia, Trevor Cohn

摘要:

机器翻译质量评估是一项非常困难的任务,这降低了它在现实世界翻译环境中的实用性。如果质量预测伴随着不确定性的测量,这种情况可以得到改善。然而,在这个任务中的模型,传统上只评估的点估计指标,不考虑预测的不确定性。我们研究质量估计的概率方法,可以提供校准良好的不确定性估计,并根据其完整的后验预测分布对其进行评估。我们还展示了这种后验信息如何在不对称风险场景中发挥作用,该场景旨在捕捉翻译工作流程中的典型情况。

英文摘要:

Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty. However, models in this task are traditionally evaluated only in terms of point estimate metrics, which do not take prediction uncertainty into account. We investigate probabilistic methods for Quality Estimation that can provide well-calibrated uncertainty estimates and evaluate them in terms of their full posterior predictive distributions. We also show how this posterior information can be useful in an asymmetric risk scenario, which aims to capture typical situations in translation workflows.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑