Papers with hypothesis oversampling
Sampling and Filtering of Neural Machine Translation Distillation Data (2021.naacl-srw)
Copied to clipboard
| Challenge: | In most of neural machine translation distillation or stealing scenarios, the highest-scoring hypothesis of the target model is used to train a new model. |
| Approach: | They propose to use the highest-scoring hypothesis of the target model (teacher) to train a new model (student). |
| Outcome: | The proposed method improves the performance of MT models in English to Czech and with reference translations. |