In-vehicle dialogue systems often contain more than one application, e.g.
Making it useful and enjoyable to use a dialogue system is always important.
To study resumption behaviour, Yang (2009), carried out a data collection where the participants were switching between an ongoing task (a card game) and a real-time task (a picture game).
A data collection has been carried out within the DICO project (see, for example, (Larsson and Villing, 2007)) to study how an additional distraction or increase in the cognitive load would affect a driver’s dialogue behaviour.
The codings from the DICO data collection has been analysed with respect to interruption and resumption of topics (interrupt-topic and resume-topic, respectively).
For both driver and passenger, the most common way to resume an interview topic is to use a declarative utterance, which is illustrated in Figure 3.
In this paper we point at some of the dialogue strategies that are used in human-human dialogue during high cognitive load when resuming to an interrupted topic.
Next we intend to implement strategies for interruption and resumption in the DICO dialogue system.