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.
@inproceedings{gervitsetal21icmi,
title={Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model},
author={Felix Gervits and Gordon Briggs and Anthony Roque and Genki Kadomatsu and Dean Thurston and Matthew Marge and Matthias Scheutz},
year={2021},
booktitle={Proceedings of ICMI},
url={https://hrilab.tufts.edu/publications/gervitsetal21icmi.pdf}
}