Search Results for author:
Found 2 papers, 1 papers with code
Self-Paced Learning for Neural Machine Translation
Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans.
Uncertainty-Aware Curriculum Learning for Neural Machine Translation
We propose uncertainty-aware curriculum learning, which is motivated by the intuition that: 1) the higher the uncertainty in a translation pair, the more complex and rarer the information it contains; and 2) the end of the decline in model uncertainty indicates the completeness of current training stage.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
