Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model
This work addresses referential ambiguity for dialogue agents in interactive settings, but it is incremental as it builds on existing empirical studies and computational approaches.
The paper tackled the problem of how dialogue agents in situated environments should ask questions to resolve referential ambiguity, by analyzing human dialogue data and developing a computational model that outperforms a baseline in varying ambiguity environments.
Dialogue agents that interact with humans in situated environments need to manage referential ambiguity across multiple modalities and ask for help as needed. However, it is not clear what kinds of questions such agents should ask nor how the answers to such questions can be used to resolve ambiguity. To address this, we analyzed dialogue data from an interactive study in which participants controlled a virtual robot tasked with organizing a set of tools while engaging in dialogue with a live, remote experimenter. We discovered a number of novel results, including the distribution of question types used to resolve ambiguity and the influence of dialogue-level factors on the reference resolution process. Based on these empirical findings we: (1) developed a computational model for clarification requests using a decision network with an entropy-based utility assignment method that operates across modalities, (2) evaluated the model, showing that it outperforms a slot-filling baseline in environments of varying ambiguity, and (3) interpreted the results to offer insight into the ways that agents can ask questions to facilitate situated reference resolution.