On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
ACL, pp. 3544-3552, 2020.
We find that Minimum Risk Training, which does not suffer from exposure bias, can be useful even when it does not increase performance on an in-domain test set: it increases performance under domain shift, reduces the number of hallucinations substantially, and makes beam search ...
The standard training algorithm in neural machine translation (NMT) suffers from exposure bias, and alternative algorithms have been proposed to mitigate this. However, the practical impact of exposure bias is under debate. In this paper, we link exposure bias to another well-known problem in NMT, namely the tendency to generate halluci...More
PPT (Upload PPT)