BJTU-Toshiba’s Submission to WMT22 Quality Estimation Shared Task

Hui Huang, Hui Di, Chunyou Li, Hanming Wu, Kazushige Ouchi, Yufeng Chen, Jian Liu, Jinan Xu


Abstract
This paper presents the BJTU-Toshiba joint submission for WMT 2022 quality estimation shared task. We only participate in Task 1 (quality prediction) of the shared task, focusing on the sentence-level MQM prediction. The techniques we experimented with include the integration of monolingual language models and the pre-finetuning of pre-trained representations. We tried two styles of pre-finetuning, namely Translation Language Modeling and Replaced Token Detection. We demonstrate the competitiveness of our system compared to the widely adopted XLM-RoBERTa baseline. Our system is also the top-ranking system on the Sentence-level MQM Prediction for the English-German language pairs.
Anthology ID:
2022.wmt-1.58
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:
621–626
Language:
URL:
https://aclanthology.org/2022.wmt-1.58
DOI:
Bibkey:
Cite (ACL):
Hui Huang, Hui Di, Chunyou Li, Hanming Wu, Kazushige Ouchi, Yufeng Chen, Jian Liu, and Jinan Xu. 2022. BJTU-Toshiba’s Submission to WMT22 Quality Estimation Shared Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 621–626, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
BJTU-Toshiba’s Submission to WMT22 Quality Estimation Shared Task (Huang et al., WMT 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.58.pdf