Learning Sparse Prototypes for Text Generation
NIPS 2020, 2020.
We propose a novel generative model that discovers a sparse prototype set automatically by optimizing a variational lower bound of the log marginal data likelihood
Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as a result of needing to store and index the entire training corpus. Further, existing methods often...More
PPT (Upload PPT)