Search Results for author:
Found 4 papers, 1 papers with code
Deliberation Networks and How to Train Them
A deliberation network consists of multiple standard sequence-to-sequence models, each one conditioned on the initial input and the output of the previous model.
Parallel Attention Forcing for Machine Translation
Attention forcing has been introduced to address the mismatch, guiding the model with the generated back-history and reference attention.
Attention Forcing for Machine Translation
This approach guides the model with the generated output history and reference attention, and can reduce the training-inference mismatch without a schedule or a classifier.
Attention Forcing for Sequence-to-sequence Model Training
This paper introduces attention forcing, which guides the model with generated output history and reference attention.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
