Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2021 | EMNLP | Conference |
Volume | Citations | PageRank |
2021.emnlp-main | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuoyang Ding | 1 | 0 | 0.68 |
Marcin Junczys-Dowmunt | 2 | 312 | 24.24 |
Matt Post | 3 | 414 | 35.72 |
Philipp Koehn | 4 | 7684 | 431.77 |