Search Results for author:
Found 3 papers, 1 papers with code
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation
Non-autoregressive neural machine translation (NAT) suffers from the multi-modality problem: the source sentence may have multiple correct translations, but the loss function is calculated only according to the reference sentence.
Mixup Decoding for Diverse Machine Translation
To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly.
Generating Diverse Translation from Model Distribution with Dropout
Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
