History-Aware Question Answering in a Blocks World Dialogue System
This work addresses the need for memory in collaborative planning for dialogue agents, but it is incremental as it builds upon an existing spatial question-answering pipeline.
The paper tackles the problem of enabling dialogue-based spatial reasoning systems to answer questions about past interactions in a physical blocks world setting, by introducing a symbolic dialogue context and a natural language understanding module for interpreting historical queries.
It is essential for dialogue-based spatial reasoning systems to maintain memory of historical states of the world. In addition to conveying that the dialogue agent is mentally present and engaged with the task, referring to historical states may be crucial for enabling collaborative planning (e.g., for planning to return to a previous state, or diagnosing a past misstep). In this paper, we approach the problem of spatial memory in a multi-modal spoken dialogue system capable of answering questions about interaction history in a physical blocks world setting. This work builds upon a full spatial question-answering pipeline consisting of a vision system, speech input and output mediated by an animated avatar, a dialogue system that robustly interprets spatial queries, and a constraint solver that derives answers based on 3-D spatial modelling. The contributions of this work include a symbolic dialogue context registering knowledge about discourse history and changes in the world, as well as a natural language understanding module capable of interpreting free-form historical questions and querying the dialogue context to form an answer.