Your right, since the output of the encoder is just a sentence embedding, you can use an existing encoding sentence embedding and use only the decoder part.
A couple of days ago, there was this post about the implementation in a paper, where the embedding came from CNN and was fed into an LSTM decoder. In this paper – as far as I could understand – the authors set the intial hidden state h_0 and zero-ed the initial cell state c_0. I would simply try this approach, as well as:
- use the embedding to set
h_0andc_0 - use a
nn.GRUwhich doesn’t have cell state
and just see how this effects the results.