Exploiting Persona Information for Diverse Generation of Conversational Responses
This work addresses the challenge of creating more realistic and varied chatbot responses for conversational AI, though it is incremental as it builds on existing persona-based models.
The paper tackled the problem of generating diverse and sustainable conversational responses by exploiting persona information, proposing a memory-augmented architecture with a conditional variational autoencoder that outperformed baselines in diversity and engagement on a benchmark dataset.
In human conversations, due to their personalities in mind, people can easily carry out and maintain the conversations. Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task. Previous work on persona-based conversational models successfully make use of predefined persona information and have shown great promise in delivering more realistic responses. And they all learn with the assumption that given a source input, there is only one target response. However, in human conversations, there are massive appropriate responses to a given input message. In this paper, we propose a memory-augmented architecture to exploit persona information from context and incorporate a conditional variational autoencoder model together to generate diverse and sustainable conversations. We evaluate the proposed model on a benchmark persona-chat dataset. Both automatic and human evaluations show that our model can deliver more diverse and more engaging persona-based responses than baseline approaches.