Dependency-aware self-attention for robust neural machine translation
Fig 5
Visualization of attention distributions in the baseline transformer (left) and the proposed dependency-aware self-attention (DASA, right).
Click through the PLOS taxonomy to find articles in your field.
For more information about PLOS Subject Areas, click here.
Visualization of attention distributions in the baseline transformer (left) and the proposed dependency-aware self-attention (DASA, right).