Proto: A Neural Cocktail for Generating Appealing Conversations
This work addresses the problem of generating appealing and coherent conversations for users, though it appears incremental as it builds on existing methods without introducing a new paradigm.
The paper tackles the challenge of creating a socialbot for engaging human conversations by integrating multiple neural and rule-based components, achieving consistent performance scores in the Alexa Prize competition.
In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: Proto. Leveraging diverse sources of world knowledge, and powered by a suite of neural and rule-based natural language understanding modules, state-of-the-art neural generators, novel state-based deterministic generators, an ensemble of neural re-rankers, a robust post-processing algorithm, and an efficient overall conversation strategy, Proto strives to be able to converse coherently about a diverse range of topics of interest to humans, and provide a memorable experience to the user. In this paper we dissect and analyze the different components and conversation strategies implemented by our socialbot, which enables us to generate colloquial, empathetic, engaging, self-rectifying, factually correct, and on-topic response, which has helped us achieve consistent scores throughout the competition.