%0 Conference Proceedings %T Levenshtein Training for Word-level Quality Estimation %A Ding, Shuoyang %A Junczys-Dowmunt, Marcin %A Post, Matt %A Koehn, Philipp %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F ding-etal-2021-levenshtein %X We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein Transformer can learn to post-edit without explicit supervision. To further minimize the mismatch between the translation task and the word-level QE task, we propose a two-stage transfer learning procedure on both augmented data and human post-editing data. We also propose heuristics to construct reference labels that are compatible with subword-level finetuning and inference. Results on WMT 2020 QE shared task dataset show that our proposed method has superior data efficiency under the data-constrained setting and competitive performance under the unconstrained setting. %R 10.18653/v1/2021.emnlp-main.539 %U https://aclanthology.org/2021.emnlp-main.539 %U https://doi.org/10.18653/v1/2021.emnlp-main.539 %P 6724-6733