Ask No More: Deciding when to guess in referential visual dialogue
This work addresses the inefficiency in referential visual dialogue for AI systems, though it is incremental as it builds on existing models.
The paper tackled the problem of making visually grounded conversational agents more efficient by deciding when to ask follow-up questions or guess, resulting in dialogues that were less repetitive and included fewer unnecessary questions.
Our goal is to explore how the abilities brought in by a dialogue manager can be included in end-to-end visually grounded conversational agents. We make initial steps towards this general goal by augmenting a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. Our analyses show that adding a decision making component produces dialogues that are less repetitive and that include fewer unnecessary questions, thus potentially leading to more efficient and less unnatural interactions.