Search Results for author:
Found 1 papers, 0 papers with code
Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation
In this paper, we conduct systematic experiments and find that scheduled sampling, while it ameliorates exposure bias by increasing model reliance on the input sequence, worsens performance when the prefix at inference time is correct, a form of catastrophic forgetting.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
