Alibaba-Translate China’s Submission for WMT2022 Metrics Shared Task
Yu Wan, Keqin Bao, Dayiheng Liu, Baosong Yang, Derek F. Wong, Lidia S. Chao, Wenqiang Lei, Jun Xie
Abstract
In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source- reference-combined evaluation scenarios into one single model. Specifically, during the model pre-training phase, we first apply the pseudo-labeled data examples to continuously pre-train UNITE. Notably, to reduce the gap between pre-training and fine-tuning, we use data cropping and a ranking-based score normalization strategy. During the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years’ WMT competitions. Specially, we collect the results from models with different pre-trained language model backbones, and use different ensembling strategies for involved translation directions.- Anthology ID:
- 2022.wmt-1.53
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 586–592
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.53
- DOI:
- Cite (ACL):
- Yu Wan, Keqin Bao, Dayiheng Liu, Baosong Yang, Derek F. Wong, Lidia S. Chao, Wenqiang Lei, and Jun Xie. 2022. Alibaba-Translate China’s Submission for WMT2022 Metrics Shared Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 586–592, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Alibaba-Translate China’s Submission for WMT2022 Metrics Shared Task (Wan et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.53.pdf