Grounding in Multi-modal Task-Oriented Collaboration

Pierre Dillenbourg, David R. Traum and Daniel Schneider
TECFA, FPSE, Université de Genève
9, Route de Drize, BAT D, CH-1227 Carouge, Switzerland,,

Paper accepted for the EuroAI&Education Conference
A postscript version (A4) is available
Abstract. This paper describes the first results of a series of experiments on multi-modal computer-supported collaborative problem solving. Pairs of subjects perform a diagnosis task (solving a murder mystery in a MOO environment), communicating by typing and drawing. While collaboration is often described as the process of building a shared conception of the problem, our protocols show that the subjects actually create multiple shared sub-spaces. These spaces are connected to each other by a functional relationship: some information in space X has to be grounded in order to ground information in space Y. The reason to dissociate these spaces is that the grounding mechanisms are different, because the nature of information to be grounded is itself different. The second observation concerns the modality of grounding. Contrary to expectations that subjects would primarily use drawings to ground verbal utterances, we observed that they use three modes of interaction: (dialogue, drawing, and also action in the MOO environment) in a more symmetrical way. Grounding is often performed across different modes (e.g. an information presented in dialogue is grounded by an action in the MOO).

1 - Introduction
2 - Grounding
3 - Experimental setting
4 - Preliminary results
5 - Conclusions
Appendix (examples from protocols)

Grounding in Multi-modal Task-Oriented Collaboration - 3 SEP 1996
Generated with Harlequin WebMaker