Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation
Abstract
Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a black-box MT system as input. Recently, a few studies indicate that as a by-product of translation, QE benefits from the model and training data's information of the MT system where the translations come from, and it is called the "glass-box QE". In this paper, we extend the definition of "glass-box QE" generally to uncertainty quantification with both "black-box" and "glass-box" approaches and design several features deduced from them to blaze a new trial in improving QE's performance. We propose a framework to fuse the feature engineering of uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality. Experiment results show that our method achieves state-of-the-art performances on the datasets of WMT 2020 QE shared task.
Cite
@article{arxiv.2109.07141,
title = {Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation},
author = {Ke Wang and Yangbin Shi and Jiayi Wang and Yuqi Zhang and Yu Zhao and Xiaolin Zheng},
journal= {arXiv preprint arXiv:2109.07141},
year = {2021}
}
Comments
Accepted by Findings of EMNLP 2021