Search Results for author:
Found 2 papers, 2 papers with code
Macro-Average: Rare Types Are Important Too
While traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency, they struggle to reflect adequacy.
Hard-Coded Gaussian Attention for Neural Machine Translation
Recent work has questioned the importance of the Transformer's multi-headed attention for achieving high translation quality.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
