M4t1ss/SoftAlignments

Single attention-matrix format for easy integration

Closed this issue · 1 comments

MaksymDel commented

If tool accepts one single attention matrix format (should be specified in the docs), it will be easy to integrate the tool with different NMT frameworks.

NMT framework contributors will only have to save attention weights in the right format to use your tool.

MaksymDel commented

Thanks for adding info about matrix format to the README.md

  • 😄1