Reproducing Self-Supervised Quality Estimation for Machine Translation

Reimplement SOTA paper from EMNLP 2021
Fine-tune pre-trained mBERT for quality estimation
Ablation study on backbones, datasets, and hyperparameters

Chahyon Ku, Daniel Cheng, Sherry Zhao, Shubhkarman Singh
University of Washington

Proposal Paper
Progress Slides
Final Paper
Final Poster
Code

Poster

Reference

Y. Zheng, Z. Tan, M. Zhang, M. Maimaiti, H. Luan, M. Sun, Q. Liu, and Y. Liu. Self-supervised quality estimation for machine translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3322–3334, Online and Punta Cana, Dominican Republic, Nov. 2021. Association for Computational Linguistics.