Skip to content

State feed with attention #5

Description

@mattiadg

I think it is strange that we need to remove the state feeding when using the attention.

The other NMT systems initialize the decoder with something coming from the encoder.
For example:
Nematus initialize the decoder with the mean of the encoder outputs
https://github.com/rsennrich/nematus/blob/73037e94884fd2d1c1d18d81686cd1f6ea32d073/nematus/nmt.py#L421-L440

While OpenNMT is passing to the decoder the states returned from the unrolling of the encoder
https://github.com/mattiadg/OpenNMT-py/blob/6bf832170421ca9c3b609ab3cfea22ae5b7fdb4e/onmt/Models.py#L140-L146

At the moment I don't understand the OpenNMT code because I don't know pytorch, but I'll try to understand what they are doing and implement it here.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions