search

atulkum / pointer_summarizer

pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"
Apache License 2.0
907 stars 242 forks source link

why using 2*hidden_dim x 2*hidden_dim linear layer in encoder? #16

Closed ziliwang closed 6 years ago

ziliwang commented 6 years ago

I found no this layer in the tensorflow implement by the author.