Structuring collaborative information-seeking dialogues

摘要

Conversational approaches to human—computer collaboration have so far mostly been employed for the design of natural language interfaces. It is claimed, however, that the conversational interaction model described in the paper can also feasibly be applied to graphical and multimodal interactions. The model comprises two interrelated parts: first, the description of local discourse structures and functional interrelations between dialogue acts to capture (local) conversational tactics, and second, the description of global structures by so-called dialogue scripts which are related to (global) information-seeking strategies. The application of the model in a multi-media information retrieval system is described in the conclusions to the paper.