search

lizekang / ITDD

The source code of our ACL2019 paper "Incremental Transformer with Deliberation Decoder for Document Grounded Conversations "
MIT License
86 stars 17 forks source link

order of attention in deliberation decoder #12

Closed dishavarshney082 closed 4 years ago

dishavarshney082 commented 4 years ago

Was there any specific reason to apply attention over knowledge base first and then on output from the first decoder in the second decoder ?