Response Diversity
Related Papers
Affect-Driven Dialog Generation
AbstractThe majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses. In this paper, we present an …...
A Multi-Persona Chatbot for Hotline Counselor Training
AbstractSuicide prevention hotline counselors aid individuals during difficult times through millions of calls and chats. A chatbot cannot safely replace a counselor, but we explore whether a chatbot can be …...
Adversarial Learning on the Latent Space for Diverse Dialog Generation
AbstractGenerating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation, but also being able to generate fluent sentences during inference. In …...
Negative Training for Neural Dialogue Response Generation
AbstractAlthough deep learning models have brought tremendous advancements to the field of open-domain dialogue response generation, recent research results have revealed that the trained models have undesirable generation behaviors, such …...