# Zero-Shot Translation Quality Estimation with Explicit Cross-Lingual Patterns

arXiv: https://arxiv.org/abs/2010.04989 · HTML: https://mlsanity.com/paper/2010.04989/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language](https://mlsanity.com/paper/2406.13698/) (2024)
- [Self-Guided Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/2105.04475/) (2021)
- [A new approach to calculating BERTScore for automatic assessment of translation quality](https://mlsanity.com/paper/2203.05598/) (2022)
- [Mismatching-Aware Unsupervised Translation Quality Estimation For Low-Resource Languages](https://mlsanity.com/paper/2208.00463/) (2022)

## Abstract (arXiv)

This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the textitmismatching issue when directly adopting BERTScore to QE. Specifically, there exist lots of mismatching errors between the source sentence and translated candidate sentence with token pairwise similarity. In response to this issue, we propose to expose explicit cross-lingual patterns, textite.g. word alignments and generation score, to our proposed zero-shot models. Experiments show that our proposed QE model with explicit cross-lingual patterns could alleviate the mismatching issue, thereby improving the performance. Encouragingly, our zero-shot QE method could achieve comparable performance with supervised QE method, and even outperforms the supervised counterpart on 2 out of 6 directions. We expect our work could shed light on the zero-shot QE model improvement.