Search Results for author: Hiroaki Saito

Found 2 papers, 0 papers with code

Deep RL with Hierarchical Action Exploration for Dialogue Generation

no code implementations22 Mar 2023 Itsugun Cho, Ryota Takahashi, Yusaku Yanase, Hiroaki Saito

Traditionally, approximate dynamic programming is employed in dialogue generation with greedy policy improvement through action sampling, as the natural language action space is vast.

Dialogue Generation Offline RL +1

A Personalized Dialogue Generator with Implicit User Persona Detection

no code implementations COLING 2022 Itsugun Cho, Dongyang Wang, Ryota Takahashi, Hiroaki Saito

Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.