Skip to content

confused about the modified loss function #6

@ScottLiao920

Description

@ScottLiao920

Hi Shawn,

It's really brilliant to come up with the "SC-LSTM" idea. I've read your paper "Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems". In section 3.4, you mentioned the modified loss function with the first term is sum of all prediction*log(label).
However, in your implementation, I noticed that you're using L1 Loss for the first term.
Any reason using L1 loss?

Regards,
Scott

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